BUDA525-Final-Project-3.R
sbranham
Thu Oct 5 19:31:39 2017
Read in the data
#data<- read.table(file.choose(),sep="\t",header=T)
##first set path to /group/bprice5
### Image of how to
dat<- read.csv("/group/bprice5/1314C-08.CSV",header=T)
head(dat)## PIDM FILE.CREATION.DATE TERM.CODE AID.YEAR PERM.CITY PERM.STATE
## 1 2266315 20160728 201308 1314 Morgantown WV
## 2 2266316 20160728 201308 1314 Bethel Park PA
## 3 2266341 20160728 201308 1314 Houston TX
## 4 2266366 20160728 201308 1314 Pittsburgh PA
## 5 2266371 20160728 201308 1314 Fairmont WV
## 6 2266376 20160728 201308 1314 Frederick MD
## PERM.ZIP.CODE PERM.CNTY.CODE X_ PERM.NATN.CODE
## 1 26505-3904 54061 Monongalia, WV 2455
## 2 15102-1368 42003 Allegheny, PA NA
## 3 77042 39015 Brown, OH NA
## 4 15241-3246 42003 Allegheny, PA NA
## 5 26554-2217 54049 Marion, WV NA
## 6 21701-4472 24021 Frederick, MD NA
## PERM.NATN.DESC PERM.PHONE..NULLED. MAIL.ADDR.LINE.1..NULLED.
## 1 Saudi Arabia NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## MAIL.ADDR.LINE.2..NULLED. MAIL.ADDR.LINE.3..NULLED. MAIL.CITY
## 1 NA NA Morgantown
## 2 NA NA Bethel Park
## 3 NA NA Morgantown
## 4 NA NA Pittsburgh
## 5 NA NA Fairmont
## 6 NA NA Frederick
## MAIL.STATE MAIL.ZIP.CODE MAIL.CNTY.CODE MAIL.CNTY.DESC MAIL.NATN.CODE
## 1 WV 26505-3904 54061 Monongalia, WV NA
## 2 PA 15102-1368 42003 Allegheny, PA NA
## 3 WV 26505-2558 54061 Monongalia, WV NA
## 4 PA 15241-3246 42003 Allegheny, PA NA
## 5 WV 26554-2217 54049 Marion, WV NA
## 6 MD 21701-4472 24021 Frederick, MD NA
## MAIL.NATN.DESC MAIL.PHONE..NULLED. ADM.ADDR.STATE.CODE ADM.ADDR.ZIP.CODE
## 1 NA WV 26508-9247
## 2 NA PA 15102-1368
## 3 NA TX 77042
## 4 NA PA 15241-3246
## 5 NA WV 26554-2217
## 6 NA MD 21701-4472
## ADM.CNTY.CODE ETHNIC.CODE ETHNIC.DESC BIRTH.DATE LEGACY
## 1 54061 4 Asian/Pacific Islander 26-Dec-84
## 2 42003 6 Race/Ethnicity Unknown 4-Jan-94 P
## 3 39015 1 White Caucasian 25-May-90
## 4 42003 1 White Caucasian 1-Aug-93 H
## 5 54049 6 Race/Ethnicity Unknown 25-Jun-77
## 6 24021 6 Race/Ethnicity Unknown 26-Nov-94 B
## LEGACY.DESC SEX.CODE CONFID.IND DEAD.IND DEAD.DATE
## 1 F N
## 2 Father and Mother are Alumni F N
## 3 M N
## 4 Husband is Alumnus M N
## 5 M N
## 6 Brother M N
## CITIZENSHIP.CODE STUDENTS.MAIN.PIN..NULLED. TERM.PIN..NULLED.
## 1 4 NA NA
## 2 1 NA NA
## 3 4 NA NA
## 4 1 NA NA
## 5 1 NA NA
## 6 1 NA NA
## VISA.TYPE.CODE.CURRENT LEGAL.NATION.CODE LEGAL.NATION.DESCR
## 1 F1 2455 Saudi Arabia
## 2 NA
## 3 F1 2455 Saudi Arabia
## 4 NA
## 5 NA
## 6 NA
## GS.ORIGL.TERM.OF.ENTRY.AT.WVU GS.TERM.CODE.EFFECTIVE GS.STATUS.CODE
## 1 201105 201308 AS
## 2 201208 201305 AS
## 3 201108 201305 AS
## 4 201208 201308 AS
## 5 201205 201308 AS
## 6 201208 201305 AS
## GS.TERM.CODE.ADMIT GS.ADMIT.TYPE.CODE GS.ADMIT.TYPE.DESC
## 1 201308 7 Masters
## 2 201208 1 First Time Freshman
## 3 201108 4 Transfer
## 4 201208 1 First Time Freshman
## 5 201205 1 First Time Freshman
## 6 201301 4 Transfer
## STUDENT.CODE.STATUS..FTF..FTT..FTG..FTP. GS.STUDENT.TYPE.CODE
## 1 FTG A
## 2 B
## 3 B
## 4 B
## 5 B
## 6 B
## GS.LEVEL.CODE GS.EXPECTED.GRAD..DATE UNUSED.NULLED. GS.SITE.CODE
## 1 GR 20160531 NA
## 2 UG 20180531 NA
## 3 UG 20150531 NA
## 4 UG 20170531 NA
## 5 UG 20150531 NA
## 6 UG 20180531 NA
## GS.RESIDENCY GS.COLLEGE.CODE GS.COLLEGE.DESC
## 1 N 14 Arts and Sciences
## 2 N 49 Reed College of Media
## 3 N 30 Engineering Mineral Resources
## 4 N 30 Engineering Mineral Resources
## 5 R 41 University College
## 6 N 30 Engineering Mineral Resources
## GS.DEGREE.CODE GS.DEGREE.DESC GS.MAJOR.CODE.1
## 1 MPS Master of Professional Studies 1478
## 2 BSJ BS in Journalism 4930
## 3 BSCHE BS in Chemical Engineering 3010
## 4 BSPNGE BS in Petroleum & Natl Gas Eng 3075
## 5 BA Bachelor of Arts 4132
## 6 BS Bachelor of Science 3049
## GS.MAJOR.CODE.1.DESC GS.MAJOR.CODE.2 GS.MAJOR.CODE.2.DESC
## 1 Applied Statistics
## 2 Direct Admit Journalism Prg
## 3 Chemical Engineering
## 4 Petroleum & Natural Gas Engr
## 5 Regents Bachelor of Arts
## 6 General Engineering
## GS.CLASSIFICATION..RANK. GS.ATTRIBUTE ACADEMIC.COMMON.MARKET
## 1 GR
## 2 SO ACM
## 3 SR ARO
## 4 SO
## 5 SR
## 6 SO
## ACADEMIC.COMMON.MARKET.DESC HIGH.SCHOOL.CODE
## 1 490075
## 2 Active/Academic Common Market 392270
## 3 Active/Reciprocity Ohio 363535
## 4 393707
## 5 491275
## 6 210535
## HIGH.SCHOOL.NAME HIGH.SCHOOL.STATE.CODE
## 1 Woodrow Wilson High School WV
## 2 Bethel Park Sr High School PA
## 3 Western Brown High School OH
## 4 Upper Saint Clair High School PA
## 5 Tucker County High School WV
## 6 Governor Thomas Johnson High MD
## HIGH.SCHOOL.ZIP.CODE WEIGHTED.GPA.IND HIGH.SCHOOL.GPA
## 1 25801-3158 NA
## 2 15102-1607 W 3.35
## 3 45154-0386 NW 2.79
## 4 15241-2331 W 3.45
## 5 26269-9302 NW 2.63
## 6 21701-4430 W 3.11
## HIGH.SCHOOL.GRAD..DATE PREVIOUS.COLL.CODE PREVIOUS.COLL.NAME
## 1 19880601 I03099 Al Jouf University
## 2 20120601 5904 West Virginia University
## 3 20110527 6827 Texas Tech University
## 4 20120601 5904 West Virginia University
## 5 19950604 0000AF Service in the Armed Forces
## 6 20120501 5230 Frederick Community College
## PREVIOUS.COLL.GPA ACT.DATE..FROM.HIGHEST.A05.
## 1 2.66
## 2 NA
## 3 3.16 1-Apr-10
## 4 4.00 1-Jun-11
## 5 3.65
## 6 4.00 1-Oct-11
## ACT.COMP.SCORE..HIGHEST.A05. ACT.ENGL..FROM.HIGHEST.A05.
## 1 NA NA
## 2 NA NA
## 3 21 21
## 4 26 26
## 5 NA NA
## 6 24 23
## ACT.MATH..FROM.HIGHEST.A05. ACT.READ..FROM.HIGHEST.A05.
## 1 NA NA
## 2 NA NA
## 3 17 22
## 4 27 22
## 5 NA NA
## 6 26 23
## ACT.SCI.REASON..FROM.HIGHEST.A05.
## 1 NA
## 2 NA
## 3 24
## 4 27
## 5 NA
## 6 24
## ACT.SUM.OF.STANDARD.SCORES..FROM.HIGHEST.A05.
## 1 NA
## 2 NA
## 3 84
## 4 120
## 5 NA
## 6 96
## SAT.RE.CENTERED.IND..FROM.HIGHEST.SMV. SAT.DATE..FROM.HIGHEST.SMV.
## 1
## 2 R 1-May-11
## 3 R 1-Mar-09
## 4 R 1-May-11
## 5 R 1-Nov-10
## 6
## SAT.TOTAL..HIGHEST.SMV. SAT.MATH..FROM.HIGHEST.SMV.
## 1 NA NA
## 2 1050 520
## 3 1030 660
## 4 1180 630
## 5 1070 590
## 6 NA NA
## SAT.VERBAL..FROM.HIGHEST.SMV. HIGHEST.ACT.ENGL HIGHEST.ACT.MATH
## 1 NA NA NA
## 2 530 NA NA
## 3 370 21 17
## 4 550 26 27
## 5 480 NA NA
## 6 NA 23 26
## HIGHEST.ACT.READING HIGHEST.ACT.SCI.REASON
## 1 NA NA
## 2 NA NA
## 3 24 24
## 4 22 27
## 5 NA NA
## 6 23 24
## HIGHEST.ACT.SUM.OF.STANDARD.SCORES HIGHEST.SAT.VERBAL HIGHEST.SAT.MATH
## 1 NA NA NA
## 2 NA 530 520
## 3 84 370 660
## 4 120 550 640
## 5 NA 490 590
## 6 96 NA NA
## GRE.VERBAL..MAX. GRE.QUANT..MAX. GRE.ANALYTIC..MAX. GRE.WRITING.ASSESS
## 1 520 600 600 NA
## 2 NA NA NA NA
## 3 NA NA NA NA
## 4 NA NA NA NA
## 5 380 400 410 NA
## 6 NA NA NA NA
## GRE.CHEM.TOTAL GRE.COMP.SCI.TOTAL GRE.ENGR.TOTAL GRE.MATH.TOTAL
## 1 NA NA NA NA
## 2 NA NA NA NA
## 3 NA NA NA NA
## 4 NA NA NA NA
## 5 NA NA NA NA
## 6 NA NA NA NA
## HRS.REG.FOR.SPRING.TERM..RE.RR.RW. HRS.REG.FOR.SUMMER.I.TERM..RE.RR.RW.
## 1 9 3
## 2 13 NA
## 3 8 10
## 4 14 4
## 5 6 6
## 6 19 6
## HRS.REG.FOR.SUMMER.II.TERM..RE.RR.RW. HRS.REG.FOR.FALL.TERM..RE.RR.RW.
## 1 NA 9
## 2 NA 18
## 3 NA 13
## 4 NA 14
## 5 NA 6
## 6 NA 15
## HRS.REG.FOR.EXTRA.TERM..RE.RR.RW. SPORTS.CODE SPORTS.DESC HONORS.CODE
## 1 NA
## 2 NA
## 3 NA
## 4 NA HONORS-SO DEAN
## 5 NA
## 6 NA
## SCHOLARS.CODE SENIOR.CITZ.CODE..SERIES.67. EXCHANGE.STUDENT.CODE
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 NA
## 6 NA
## WEEBLES.CODE SSS.TRIO.CODE UNUSED.CODE.G UNUSED.CODE.H PROMISE.CODE
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA PROMISE
## 5 NA NA PROMISE
## 6 NA NA PROMISE
## UNUSED.CODE.J VETERAN.CODE VETERAN.DESC BOT.INSTIT..NULLED.
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 I 33 NA
## 6 NA
## BOT.YR.OF.REPORT..NULLED. BOT.LEVL.CODE..NULLED.
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## FILLER..WAS.SCHOOL.BUDGET. UNMET.NEED FED.PELL.GRANT FED.SUPPL.ED.OPP
## 1 0 0 0 0
## 2 0 550 795 0
## 3 0 0 0 0
## 4 0 6 3295 0
## 5 0 0 0 0
## 6 0 0 0 0
## OTHER.FED.GRANTS.AND.SCHOLARS WV.HIGHER.ED.GRANT.PROG PROMISE.SCHOLARS
## 1 0 0 0
## 2 0 0 0
## 3 0 0 0
## 4 0 0 0
## 5 0 0 0
## 6 0 0 0
## HEAPS..NOT.WF.DEVLPMNT.COMP. HEAPS.WF.DEVLPMNT.COMP
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## UNDERWOOD.SMITH.TEACHER.SCHOLARS WV.ENG..SCI..AND.TECH.SCHOLARS
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## OTHER.WV.STATE.GRANTS.AND.SCHOLARS OUT.OF.STATE.GRANTS.AND.SCHOLARS
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 556
## 5 0 0
## 6 0 0
## MISC.GRANTS.AND.SCHOLARS PROC..RULE.NO..49.UG.TUI.FEE.WAIV.ATHL
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## PROC..RULE.NO..49.UG.TUI.FEE.WAIV.ACAD
## 1 0
## 2 3000
## 3 0
## 4 4000
## 5 0
## 6 1500
## PROC..RULE.NO..49.UG.TUI.FEE.WAIV.NEED...OTHER
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## PROC..RULE.NO..49.GR...PR.TUI.FEE.WAIVS
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## INST.GRANTS.AND.SCHOLARS.ATHLETIC INST.GRANTS.AND.SCHOLARS.ACADEMIC
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## INST.GRANTS.AND.SCHOLARS.OTHER FED.WORK.STUDY..FWS..PROGRAM
## 1 0 0
## 2 1500 0
## 3 0 0
## 4 2000 0
## 5 0 0
## 6 0 0
## OTHER.FED.EMPLOYMENT INST.EMPLOYMENT
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## FILLER..WAS.FED.STAFFORD.LOAN....SUBSIDIZED.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## FILLER..WAS.FED.STAFFORD.LOAN....UNSUBSIDIZED.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## FED.DIRECT.LOAN....SUBSIDIZED FED.DIRECT.LOAN....UNSUBSIDIZED
## 1 0 0
## 2 4454 1980
## 3 0 0
## 4 4454 1980
## 5 0 0
## 6 0 0
## FED.DIRECT.PLUS FED.PERKINS.LOAN FILLER..WAS.FED.PLUS. OTHER.FED.LOANS
## 1 0 0 0 0
## 2 18456 0 0 0
## 3 0 0 0 0
## 4 14027 0 0 0
## 5 0 0 0 0
## 6 0 0 0 0
## MED.STUDENT.LOAN INST.LOANS MISC.LOANS VETS.AND.ACTIVE.DUTY.MIL.BENS
## 1 0 0 0 0
## 2 0 0 0 0
## 3 0 0 0 0
## 4 0 0 0 0
## 5 0 0 0 7789
## 6 0 0 30419 0
## VOC.REHAB.BENS OTHER.ED.BENS BOT.STATE.CODE.NULLED. NSLDS.SUB
## 1 0 24369 NA NA
## 2 0 0 NA 3500
## 3 0 0 NA 8000
## 4 0 0 NA 3500
## 5 0 0 NA NA
## 6 0 0 NA 3500
## NSLDS.UNSUB NSLDS.SUB.AND.UNSUB.TOTAL NSLDS.PERKINS.TOTAL
## 1 NA NA NA
## 2 2000 5500 NA
## 3 3980 11980 NA
## 4 2000 5500 NA
## 5 12000 12000 NA
## 6 2000 5500 NA
## FATHERS.HI.GRADE MOTHERS.HI.GRADE EXPECTED.TOT.FAM.CONT..EFC.
## 1 NA NA NA
## 2 2 3 4834
## 3 3 3 46
## 4 3 2 2396
## 5 3 2 13870
## 6 2 3 21298
## SPRING.TERM.ORIENTATION.IND SUM.I.TERM...ORIEN.IND
## 1
## 2
## 3
## 4
## 5
## 6
## SUM.II.TERM...ORIEN.IND FALL.TERM...ORIEN.IND EXTRA.TERM...ORIEN.IND
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## SPRING.TERM.APPLICATION.IND SUM.I.TERM...APPL.IND SUM.II.TERM...APPL.IND
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 Y NA
## 6 NA
## FALL.TERM...APPL.IND EXTRA.TERM...APPL.IND SPRING.TERM.ADM.DEC.MADE.IND
## 1 Y NA
## 2 Y NA
## 3 NA
## 4 NA
## 5 NA
## 6 Y NA
## SUM.I.TERM...ADM.DEC.MADE.IND SUM.II.TERM...ADM.DEC.MADE.IND
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 Y NA
## 6 NA
## FALL.TERM...ADM.DEC.MADE.IND EXTRA.TERM...ADM.DEC.MADE.IND
## 1 Y NA
## 2 Y NA
## 3 NA
## 4 NA
## 5 NA
## 6 Y NA
## SPRING.TERM.ENR.IND SUM.I.TERM...ENR.IND SUM.II.TERM...ENR.IND
## 1 Y Y NA
## 2 Y NA
## 3 Y Y NA
## 4 Y Y NA
## 5 Y Y NA
## 6 Y Y NA
## FALL.TERM...ENR.IND EXTRA.TERM...ENR.IND SPRING.TERM.REG.IND
## 1 Y NA Y
## 2 Y NA Y
## 3 Y NA Y
## 4 Y NA Y
## 5 Y NA Y
## 6 Y NA Y
## SUM.I.TERM...REG.IND SUM.II.TERM...REG.IND FALL.TERM...REG.IND
## 1 Y NA Y
## 2 NA Y
## 3 Y NA Y
## 4 Y NA Y
## 5 Y NA Y
## 6 Y NA Y
## EXTRA.TERM...REG.IND SPRING.TERM.APPL.FOR.DEGR.IND
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## SUM.I.TERM...APPL.FOR.DEGR.IND SUM.II.TERM...APPL.FOR.DEGR.IND
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## FALL.TERM...APPL.FOR.DEGR.IND EXTRA.TERM...APPL.FOR.DEGR.IND
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## SPRING.TERM.GRAD.IND SUM.I.TERM...GRAD.IND SUM.II.TERM...GRAD.IND
## 1 Y NA
## 2 NA
## 3 Y NA
## 4 NA
## 5 NA
## 6 NA
## FALL.TERM...GRAD.IND EXTRA.TERM...GRAD.IND BORN.BEFORE.DATE.IND
## 1 Y NA NA
## 2 NA 2
## 3 NA 2
## 4 NA 2
## 5 NA 2
## 6 NA 2
## GRAD.OR.PROF.IND MARRIED.IND HAVE.CHILD.SUPPORT.IND US.INCOME
## 1 NA NA NA NA
## 2 2 2 2 2130
## 3 2 2 2 3715
## 4 2 2 2 NA
## 5 2 2 2 5296
## 6 2 2 2 2900
## USER.DEFINES.FIELD..VARIES. STD.CAMP.CODE DEPEND.STAT AGI.FOR.PAR
## 1 NA SWA NA
## 2 NA SWA D 68307
## 3 NA SWA D 36414
## 4 NA SWA D 59068
## 5 NA SWA D 119268
## 6 NA SWA D 123000
## NUM.IN.PARS.HOUSE NUM.IN.STUDS.HOUSE ACAD.EXCEL.L1.WAIV....0WVAE1
## 1 NA NA 0
## 2 5 5 0
## 3 4 NA 0
## 4 4 NA 0
## 5 4 NA 0
## 6 4 NA 0
## ACAD.EXCEL.L2.WAIV....0WVAE2 BLUE...GOLD.WAIV.LEVEL.1...0WVBG1
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 4000
## 5 0 0
## 6 0 0
## BLUE...GOLD.WAIV.LEVEL.2...0WVBG2 SCHOLAR.S.WAIV.EQUIVALENT...0WVEQV
## 1 0 0
## 2 3000 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 1500 0
## FILLER..WAS.ACADC.COMP.GRANT. FILLER..WAS.NATN.SMART.GRANT.
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## GEAR.UP..GAINING.EARLY.AWARE.READ..UG.PROGS. FED.DIRECT.GRAD.PLUS
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## FILLER..WAS.STAFFORD.GRAD.PLUS. OTHER.CATS.UNDER.PB.49 NEW.ETHNIC.CODE
## 1 0 0 1
## 2 0 0 1
## 3 0 0 1
## 4 0 0 1
## 5 0 0 1
## 6 0 0 1
## AMER.IND.OR.ALSK.NATV.IND ASIAN.IND BLACK.OR.AFRICAN.AMER.IND
## 1 N N N
## 2 N N N
## 3 N N N
## 4 N N N
## 5 N N N
## 6 N N N
## NATV.HAWAIIAN.OR.PACIF.ISL.IND WHITE.IND HISPANIC.IND UNKNOWN.RACE.IND
## 1 N Y N N
## 2 N Y N N
## 3 N N N Y
## 4 N Y N N
## 5 N Y N N
## 6 N Y N N
## EXTRA.RACE.CODES UG.TUI.FEE.WAIVS.CHILD.SPOUS
## 1 NA 0
## 2 NA 0
## 3 NA 0
## 4 NA 0
## 5 NA 0
## 6 NA 0
## UG.TUI.FEE.WAIVS.INDS.OVER.65 UG.TUI.FEE.WAIVS.HS.GRADS.IN.FOSTER.CARE
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## UG.TUI.FEE.WAIVS.PRPL.HRT.MDL.OF.HNR.RECIPS
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## UG.TUI.FEE.WAIVS.CHILD.SPOUS.OF.ARMED.FORCES.KILL.IN.ACT..ETC.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## UG.TUI.FEE.WAIVS.HLTH.SCI.TECH.ACAD..HSTA.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## UG.TUI.FEE.WAIVS.EMP.OF.THE.INST
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## UG.TUI.FEE.WAIVS.SPOUS.DEPEND.OF.EMP.OF.THE.INST YELLOW.RIBBON.IND
## 1 0 N
## 2 0 N
## 3 0 N
## 4 0 N
## 5 0 N
## 6 0 N
## YELLOW.RIBBON.INST.AMT YELLOW.RIBBON.VETS.ADMIN.AMT
## 1 0 0
## 2 0 0
## 3 0 0
## 4 0 0
## 5 0 0
## 6 0 0
## IPEDS.LIVING.ARRANGE.CODE HEPC.ID..NULLED. GED.SCORE TASCP.SCORE
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## EXPECTED.FAMILY.CONTRIBUTION..EFC. HOUS.ARRANGE..HEPC.LIV.ARRANGES.CODE.
## 1 99999998 NA
## 2 4834 NA
## 3 99999998 NA
## 4 2396 NA
## 5 99999998 NA
## 6 21298 NA
## MISSING.HEPC.STU.RECORDS.IND..NULLED. HEPC.STU.FILE.SUB.YEAR..NULLED.
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## HEPC.STU.FILE.SUB.TERM..NULLED.
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 NA
## 6 NAdim(dat)## [1] 16480 257#Additional packages
install.packages("dae") #Allows combining factors## Installing package into '/users/sbranham/R/x86_64-redhat-linux-gnu-library/3.3'
## (as 'lib' is unspecified)library(dae)## Loading required package: ggplot2install.packages("scales")## Installing package into '/users/sbranham/R/x86_64-redhat-linux-gnu-library/3.3'
## (as 'lib' is unspecified)## Warning in install.packages("scales"): installation of package 'scales' had
## non-zero exit statuslibrary(scales)
install.packages("gsubfn")## Installing package into '/users/sbranham/R/x86_64-redhat-linux-gnu-library/3.3'
## (as 'lib' is unspecified)library(gsubfn)## Loading required package: proto## Warning in fun(libname, pkgname): couldn't connect to display ":0"install.packages("alr4")## Installing package into '/users/sbranham/R/x86_64-redhat-linux-gnu-library/3.3'
## (as 'lib' is unspecified)library(alr4)## Loading required package: car## Loading required package: effects## Loading required package: carData##
## Attaching package: 'carData'## The following objects are masked from 'package:car':
##
## Guyer, UN, Vocab## lattice theme set by effectsTheme()
## See ?effectsTheme for details.#Subpopulations we want to work with
#SubPop 1. First Time Freshman
#Create subset of data with only First Time Freshmen (firstTimeFresh)
firstTimeFresh <- dat[which(dat$GS.ADMIT.TYPE.DESC == "First Time Freshman"),]
dim(firstTimeFresh)## [1] 8590 257#Can create other subpopulations if needed (grad students, seniors, etc)
#Dependent variables
#Personal attributes
#1. Gender (studentGender)
studentGender <- as.factor(firstTimeFresh$SEX.CODE)
summary(studentGender)## F M
## 3922 4668levels(studentGender)## [1] "F" "M"#2. Ethnicity (studentEthn)
studentEthn <- factor(firstTimeFresh$ETHNIC.CODE, labels = c("White", "Black", "Hispanic", "Asian", "Native", "Unknown"))
summary(studentEthn)## White Black Hispanic Asian Native Unknown NA's
## 3435 446 79 106 16 4464 44levels(studentEthn)## [1] "White" "Black" "Hispanic" "Asian" "Native" "Unknown"#3. Major (degreeF)
degreeF <- firstTimeFresh$GS.DEGREE.DESC
summary(degreeF) #Shows degrees w/ 0 students in it## Associate of Applied Sci
## 0 98
## Associate of Arts Bachelor Electronic Engr
## 847 2
## Bachelor Engr Tech Bachelor of Applied Science
## 4 0
## Bachelor of Arts Bachelor of Fine Arts
## 2040 113
## Bachelor of Multidisc. Studies Bachelor of Music
## 150 81
## Bachelor of Science Bachelor of Science in Nursing
## 3430 13
## Bachelor of Social Work BS in Aerospace Engineering
## 42 62
## BS in Agriculture BS in Biometric Systems
## 58 11
## BS in Business Administration BS in Chemical Engineering
## 797 51
## BS in Civil Engineering BS in Computer Engineering
## 53 29
## BS in Computer Science BS in Electrical Engineering
## 59 44
## BS in Forestry BS in Industrial Engineering
## 40 37
## BS in Journalism BS in Landscape Architecture
## 238 27
## BS in Mechanical Engineering BS in Mining Engineering
## 63 11
## BS in Petroleum & Natl Gas Eng BS in Physical Education
## 42 17
## BS in Recreation Degree Not Declared
## 17 111
## Doctor of Audiology Doctor of Dental Surgery
## 0 0
## Doctor of Education Doctor of Jurisprudence
## 0 0
## Doctor of Medicine Doctor of Musical Arts
## 0 0
## Doctor of Nursing Practice Doctor of Pharmacy
## 0 0
## Doctor of Philosophy Doctor of Physical Therapy
## 0 0
## Master of Agriculture Master of Arts
## 0 0
## Master of Business Admnstrtn Master of Fine Arts
## 0 0
## Master of Landscape Arc Master of Legal Studies
## 0 0
## Master of Music Master of Occupational Therapy
## 0 0
## Master of Professional Acct Master of Professional Studies
## 0 0
## Master of Public Admnstrtn Master of Public Health
## 0 0
## Master of Science Master of Science in Forestry
## 0 0
## Master of Science in Nursing Master of Social Work
## 0 0
## Master's in Health Sciences MS in Aerospace Engineering
## 0 0
## MS in Chemical Engineering MS in Civil Engineering
## 0 0
## MS in Computer Science MS in Electrical Engineering
## 0 0
## MS in Engineering MS in Industrial Engineering
## 0 0
## MS in Journalism MS in Mechanical Engineering
## 0 0
## MS in Mining Engineering MS in Petrl & Natural Gas Engr
## 0 0
## MS in Software Engineering Regents Bachelor of Arts
## 0 3degreeF <- factor(degreeF) #Excludes unused levels
summary(degreeF) #All majors have at least 1 student it in## Associate of Applied Sci Associate of Arts
## 98 847
## Bachelor Electronic Engr Bachelor Engr Tech
## 2 4
## Bachelor of Arts Bachelor of Fine Arts
## 2040 113
## Bachelor of Multidisc. Studies Bachelor of Music
## 150 81
## Bachelor of Science Bachelor of Science in Nursing
## 3430 13
## Bachelor of Social Work BS in Aerospace Engineering
## 42 62
## BS in Agriculture BS in Biometric Systems
## 58 11
## BS in Business Administration BS in Chemical Engineering
## 797 51
## BS in Civil Engineering BS in Computer Engineering
## 53 29
## BS in Computer Science BS in Electrical Engineering
## 59 44
## BS in Forestry BS in Industrial Engineering
## 40 37
## BS in Journalism BS in Landscape Architecture
## 238 27
## BS in Mechanical Engineering BS in Mining Engineering
## 63 11
## BS in Petroleum & Natl Gas Eng BS in Physical Education
## 42 17
## BS in Recreation Degree Not Declared
## 17 111
## Regents Bachelor of Arts
## 3levels(degreeF)## [1] "Associate of Applied Sci" "Associate of Arts"
## [3] "Bachelor Electronic Engr" "Bachelor Engr Tech"
## [5] "Bachelor of Arts" "Bachelor of Fine Arts"
## [7] "Bachelor of Multidisc. Studies" "Bachelor of Music"
## [9] "Bachelor of Science" "Bachelor of Science in Nursing"
## [11] "Bachelor of Social Work" "BS in Aerospace Engineering"
## [13] "BS in Agriculture" "BS in Biometric Systems"
## [15] "BS in Business Administration" "BS in Chemical Engineering"
## [17] "BS in Civil Engineering" "BS in Computer Engineering"
## [19] "BS in Computer Science" "BS in Electrical Engineering"
## [21] "BS in Forestry" "BS in Industrial Engineering"
## [23] "BS in Journalism" "BS in Landscape Architecture"
## [25] "BS in Mechanical Engineering" "BS in Mining Engineering"
## [27] "BS in Petroleum & Natl Gas Eng" "BS in Physical Education"
## [29] "BS in Recreation" "Degree Not Declared"
## [31] "Regents Bachelor of Arts"#4. Type of major (degreeType)
#Some majors are associates, and some are bachelors, want to split assocDegree and bachelDegree and otherDegree
assocDegree1 <- factor(degreeF == "Associate of Applied Sci")
assocDegree2 <- factor(degreeF == "Associate of Arts")
notDecDegree <- factor(degreeF == "Degree Not Declared")
regDegree <- factor(degreeF == "Regents Bachelor of Arts")
degreeType <- fac.combine(list(assocDegree1, assocDegree2, notDecDegree, regDegree))
degreeType <- factor(degreeType, labels = c("Bachelor Degree", "Regent Degree", "Degree Not Declared", "Associate Arts", "Associate Applied Sci"))
summary(degreeType)## Bachelor Degree Regent Degree Degree Not Declared
## 7531 3 111
## Associate Arts Associate Applied Sci
## 847 98levels(degreeType)## [1] "Bachelor Degree" "Regent Degree" "Degree Not Declared"
## [4] "Associate Arts" "Associate Applied Sci"#Location attributes
#1. Student location by state (studentLoc)
studentLoc <- as.factor(firstTimeFresh$MAIL.STATE)
summary(studentLoc)## AB AE AK AL AP AR AZ BC CA CO CT DC DE FL
## 0 0 1 1 6 1 4 2 2 44 10 73 93 71 64
## FR GA GU HI IA ID IL IN KS KY LA MA MB MD ME
## 22 38 0 0 6 0 35 13 2 9 2 60 0 778 3
## MI MN MO MP MS MT NB NC ND NE NH NJ NM NV NY
## 19 5 5 0 2 1 0 45 1 1 9 473 1 4 291
## OH OK ON OR PA PQ PR RI SC SD TN TX UT VA VT
## 302 5 4 3 935 0 1 7 21 1 20 50 1 673 8
## WA WI WV WY
## 8 13 4341 0levels(studentLoc)## [1] "" "AB" "AE" "AK" "AL" "AP" "AR" "AZ" "BC" "CA" "CO" "CT" "DC" "DE"
## [15] "FL" "FR" "GA" "GU" "HI" "IA" "ID" "IL" "IN" "KS" "KY" "LA" "MA" "MB"
## [29] "MD" "ME" "MI" "MN" "MO" "MP" "MS" "MT" "NB" "NC" "ND" "NE" "NH" "NJ"
## [43] "NM" "NV" "NY" "OH" "OK" "ON" "OR" "PA" "PQ" "PR" "RI" "SC" "SD" "TN"
## [57] "TX" "UT" "VA" "VT" "WA" "WI" "WV" "WY"studentLoc <- factor(studentLoc) #remove unused levels
summary(studentLoc)## AE AK AL AP AR AZ BC CA CO CT DC DE FL FR GA
## 1 1 6 1 4 2 2 44 10 73 93 71 64 22 38
## IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC
## 6 35 13 2 9 2 60 778 3 19 5 5 2 1 45
## ND NE NH NJ NM NV NY OH OK ON OR PA PR RI SC
## 1 1 9 473 1 4 291 302 5 4 3 935 1 7 21
## SD TN TX UT VA VT WA WI WV
## 1 20 50 1 673 8 8 13 4341prop.table(table(studentLoc)) #50% of the students come from WV ## studentLoc
## AE AK AL AP AR
## 0.0001164144 0.0001164144 0.0006984866 0.0001164144 0.0004656577
## AZ BC CA CO CT
## 0.0002328289 0.0002328289 0.0051222352 0.0011641444 0.0084982538
## DC DE FL FR GA
## 0.0108265425 0.0082654249 0.0074505239 0.0025611176 0.0044237485
## IA IL IN KS KY
## 0.0006984866 0.0040745052 0.0015133877 0.0002328289 0.0010477299
## LA MA MD ME MI
## 0.0002328289 0.0069848661 0.0905704307 0.0003492433 0.0022118743
## MN MO MS MT NC
## 0.0005820722 0.0005820722 0.0002328289 0.0001164144 0.0052386496
## ND NE NH NJ NM
## 0.0001164144 0.0001164144 0.0010477299 0.0550640279 0.0001164144
## NV NY OH OK ON
## 0.0004656577 0.0338766007 0.0351571595 0.0005820722 0.0004656577
## OR PA PR RI SC
## 0.0003492433 0.1088474971 0.0001164144 0.0008149010 0.0024447031
## SD TN TX UT VA
## 0.0001164144 0.0023282887 0.0058207218 0.0001164144 0.0783469150
## VT WA WI WV
## 0.0009313155 0.0009313155 0.0015133877 0.5053550640#2. In and out of state indicator (stateIndicator)
stateIndicator <- factor(studentLoc == "WV", labels = c("Out-of-State", "In-State"))
summary(stateIndicator)## Out-of-State In-State
## 4249 4341#3. Proximity indicator (proxStudentType)
#Assumptions:
#In-state students will commute to Morgantown, the furthest out, the more the student will require assistance, after a certain distance, it makes no sense to commute and we can assume the student will move to Morgantown.
#Assume the population from Monongalia will commute
#Assume the population from the following counties will also commute (~1 hour) and should be eligible for additional assistance: Preston, Taylor, Marion
#For all counties outside of this radius we assume would move to Morgantown
#Monongalia == shortCommuteStudent
#Preston, Taylor, Marion == longCommuteStudent
#Every other in-state counties == resStudent
shortCommuteStudent <- factor(firstTimeFresh$MAIL.CNTY.DESC == "Monongalia, WV")
longCommuteStudent <- factor(firstTimeFresh$MAIL.CNTY.DESC == "Preston, WV" | firstTimeFresh$MAIL.CNTY.DESC == "Taylor, WV" | firstTimeFresh$MAIL.CNTY.DESC == "Marion, WV")
summary(shortCommuteStudent) #1529## FALSE TRUE
## 7061 1529summary(longCommuteStudent) #227## FALSE TRUE
## 8363 227proxStudentType <- fac.combine(list(shortCommuteStudent, longCommuteStudent))
summary(proxStudentType)## 1 2 3
## 6834 227 1529proxStudentType <- factor(proxStudentType, labels = c("Res or Out-of-State", "Long Commute", "Short Commute"))
#Affinity
affinityStatus <- as.factor(firstTimeFresh$LEGACY.DESC == "" | firstTimeFresh$LEGACY.DESC == "*No Family Member is Alumnus")
affinityStatus <- factor(affinityStatus, labels = c("Some Affinity", "No Affinity"))
summary(affinityStatus)## Some Affinity No Affinity
## 3718 4872#Affordability attributes
expectedFamContrib <- rescale(firstTimeFresh$EXPECTED.TOT.FAM.CONT..EFC, to = c(0,100))
summary(expectedFamContrib)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.000 1.351 9.965 18.080 25.160 100.000 436#Academic Achievement attributes
#The academic achievement variables from the data are:
#HIGH.SCHOOL.GPA
#PREVIOUS.COLL.GPA
#HIGHEST.ACT.SUM.OF.STANDARD.SCORES
#SAT.TOTAL..HIGHEST.SMV.
#GED.SCORE
#Not all of these variables are ready for analysis, so this section will work on checking through each academic achievement variable and getting it ready.
#HIGH.SCHOOL.GPA
#go ahead and Weight the Unweighted HIGH.SCHOOL.GPAs from 0 to 5.0 instead of 0 to 4.0 while referencing WEIGHTED.GPA.IND variable.
highSchoolGPA <- ifelse((firstTimeFresh$WEIGHTED.GPA.IND=="NW") & (firstTimeFresh$HIGH.SCHOOL.GPA <=4), firstTimeFresh$HIGH.SCHOOL.GPA * 1.25, ifelse(firstTimeFresh$WEIGHTED.GPA.IND == "W", firstTimeFresh$HIGH.SCHOOL.GPA * 1, NA))
#PREVIOUS.COLL.GPA
#Need to mark the values that are greater than 4.0 as NA. This is invalid information.
prevColGPA <- ifelse((firstTimeFresh$PREVIOUS.COLL.GPA > 4), NA, firstTimeFresh$PREVIOUS.COLL.GPA)
#HIGHEST.ACT.SUM.OF.STANDARD.SCORES
highestACT <- firstTimeFresh$HIGHEST.ACT.SUM.OF.STANDARD.SCORES
#SAT.TOTAL..HIGHEST.SMV.
totalSAT <- firstTimeFresh$SAT.TOTAL..HIGHEST.SMV.
#GED.SCORE
#remove the "G" from GED.SCORE to create a numeric value for scaling
scoreGED <- gsub("G", "", firstTimeFresh$GED.SCORE)
scoreGED <- as.numeric(as.character(scoreGED))
summary(scoreGED) # worked. Values 0 to 75.## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.00 51.00 55.00 55.44 61.00 75.00 8425#The 5 academic variables that we will use are:
#highSchoolGPA - Values 1.25 to 5.00
#prevColGPA - Values 0.00 to 4.00
#highestACT - Values 33 to 142
#totalSAT - Values 305 to 1600
#scoreGED - Values 0 to 75.
#Now that we have the 5 academic achievement variables formatted properly, we can scale the academic variables from 0 to 100 to create an even scale.
highSchoolGPA <- rescale(highSchoolGPA, to = c(1,100))
prevColGPA <- rescale(prevColGPA, to = c(1,100))
highestACT <- rescale(highestACT, to = c(1,100))
totalSAT <- rescale(totalSAT, to = c(1,100))
scoreGED <- rescale(scoreGED, to = c(1,100))
#The 5 academic achievement variables are now each on a percentile scale of 0 to 100. We just need to get the (count of which 5 academic variables in each row that are not NA) and use this to divide the (sum of the 5 academic variables in each row) to create the SCALED.ACADEMIC.ACHIEVEMENT variable that will be between 0 to 100 for each student.
# First Sum the 5 variables together
academAchievSum <- cbind.data.frame(highSchoolGPA, prevColGPA, highestACT, totalSAT, scoreGED)
academAchiev <- rowSums(academAchievSum[, c("highSchoolGPA", "prevColGPA", "highestACT", "totalSAT", "scoreGED")], na.rm = TRUE)
summary(academAchiev)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 157.0 205.4 204.3 252.0 413.7#Second get a count of NAs within the 5 variables by row.
countNA <- rowSums(is.na(academAchievSum[, c("highSchoolGPA", "prevColGPA", "highestACT", "totalSAT", "scoreGED")]))
summary(countNA)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.000 2.000 1.856 2.000 5.000#Create the SCALED.ACADEMIC.ACHIEVEMENT variable
scaledAcademAchiev <- academAchiev / (5 - countNA)
summary(scaledAcademAchiev)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 13.60 57.17 65.44 64.69 72.64 100.00 1#Independent variables
#Define 21 different grant types - this code only works for FTF, rework the code later to be able to work with any subpopulation we want
#Federal aid
fedDirLoan_unsub <- firstTimeFresh$FED.DIRECT.LOAN....UNSUBSIDIZED
fedDirLoan_sub <- firstTimeFresh$FED.DIRECT.LOAN....SUBSIDIZED
fedDirPlus <- firstTimeFresh$FED.DIRECT.PLUS
fedPellGrant <- firstTimeFresh$FED.PELL.GRANT
fedSupOpp <- firstTimeFresh$FED.SUPPL.ED.OPP
fedOther <- firstTimeFresh$OTHER.FED.GRANTS.AND.SCHOLARS + firstTimeFresh$OTHER.FED.LOANS
#Misc grants
miscGrants <- firstTimeFresh$MISC.GRANTS.AND.SCHOLARS
outOfStateGrant <- firstTimeFresh$OUT.OF.STATE.GRANTS.AND.SCHOLARS
medStudLoan <- firstTimeFresh$MED.STUDENT.LOAN
#WVU grants
rule49Grant <- firstTimeFresh$PROC..RULE.NO..49.GR...PR.TUI.FEE.WAIVS + firstTimeFresh$PROC..RULE.NO..49.UG.TUI.FEE.WAIV.ACAD + firstTimeFresh$PROC..RULE.NO..49.UG.TUI.FEE.WAIV.ATHL + firstTimeFresh$PROC..RULE.NO..49.UG.TUI.FEE.WAIV.NEED...OTHER
instEmployAid <- firstTimeFresh$INST.EMPLOYMENT
instGrantAcademic <- firstTimeFresh$INST.GRANTS.AND.SCHOLARS.ACADEMIC
instGrantAthletic <- firstTimeFresh$INST.GRANTS.AND.SCHOLARS.ATHLETIC
instGrantOther <- firstTimeFresh$INST.GRANTS.AND.SCHOLARS.OTHER
#West Virgina (state) grants
wvHigherEdGrant <- firstTimeFresh$WV.HIGHER.ED.GRANT.PROG
promScholars <- firstTimeFresh$PROMISE.SCHOLARS
wvOther <- firstTimeFresh$OTHER.WV.STATE.GRANTS.AND.SCHOLARS
#Build our data of independent and dependent variables
#WVU financial aid variables - will have to be combined into 1 independent variable
finDataTableWVU <- cbind.data.frame(rule49Grant, instEmployAid, instGrantAcademic, instGrantAthletic, instGrantOther)
#Calculate total WVU award pool
totalAwardWVU <- rule49Grant + instEmployAid + instGrantAcademic + instGrantAthletic + instGrantOther
sum(totalAwardWVU)## [1] 18510879#The total WVU award amount for the years 2013-14 for first time freshman is 18.5$MM
#Calculate total non WVU award pool
totalAwardnonWVU <- fedDirLoan_unsub + fedDirLoan_sub + fedDirPlus + fedPellGrant + fedSupOpp + fedOther + miscGrants + outOfStateGrant + medStudLoan + wvHigherEdGrant + promScholars + wvOther
sum(totalAwardnonWVU) #66.5$MM## [1] 66540034#Calculate Promise Scholar award
totalAwardScholar <- promScholars
sum(totalAwardScholar) #7.5$MM## [1] 7508903#Add the dependent variables to finDataTable
studentGender -> finDataTableWVU$studentGender
studentEthn -> finDataTableWVU$studentEthn
degreeF -> finDataTableWVU$degreeF
degreeType -> finDataTableWVU$degreeType
studentLoc -> finDataTableWVU$studentLoc
stateIndicator -> finDataTableWVU$stateIndicator
proxStudentType -> finDataTableWVU$proxStudentType
highSchoolGPA -> finDataTableWVU$highSchoolGPA
prevColGPA -> finDataTableWVU$prevColGPA
highestACT -> finDataTableWVU$highestACT
totalSAT -> finDataTableWVU$totalSAT
scoreGED -> finDataTableWVU$scoreGED
scaledAcademAchiev -> finDataTableWVU$scaledAcademAchiev
affinityStatus -> finDataTableWVU$affinityStatus
expectedFamContrib -> finDataTableWVU$expectedFamContrib
summary(finDataTableWVU)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0 Median : 0.0 Median : 0.0 Median : 0.0
## Mean : 950 Mean : 189.3 Mean : 526.6 Mean : 301.2
## 3rd Qu.: 0 3rd Qu.: 0.0 3rd Qu.: 0.0 3rd Qu.: 0.0
## Max. :21336 Max. :17233.0 Max. :15603.0 Max. :41170.0
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:3922 White :3435
## 1st Qu.: 0.0 M:4668 Black : 446
## Median : 0.0 Hispanic: 79
## Mean : 187.8 Asian : 106
## 3rd Qu.: 0.0 Native : 16
## Max. :9338.0 Unknown :4464
## NA's : 44
## degreeF degreeType
## Bachelor of Science :3430 Bachelor Degree :7531
## Bachelor of Arts :2040 Regent Degree : 3
## Associate of Arts : 847 Degree Not Declared : 111
## BS in Business Administration : 797 Associate Arts : 847
## BS in Journalism : 238 Associate Applied Sci: 98
## Bachelor of Multidisc. Studies: 150
## (Other) :1088
## studentLoc stateIndicator proxStudentType
## WV :4341 Out-of-State:4249 Res or Out-of-State:6834
## PA : 935 In-State :4341 Long Commute : 227
## MD : 778 Short Commute :1529
## VA : 673
## NJ : 473
## OH : 302
## (Other):1088
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 1.00 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.: 58.97 1st Qu.: 73.27 1st Qu.: 45.50 1st Qu.: 45.00
## Median : 73.43 Median : 85.64 Median : 54.59 Median : 52.62
## Mean : 71.21 Mean : 82.45 Mean : 55.49 Mean : 53.08
## 3rd Qu.: 84.87 3rd Qu.: 95.79 3rd Qu.: 64.58 3rd Qu.: 60.23
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :100.00
## NA's :145 NA's :3510 NA's :2074 NA's :1793
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 1.00 Min. : 13.60 Some Affinity:3718
## 1st Qu.: 68.32 1st Qu.: 57.17 No Affinity :4872
## Median : 73.60 Median : 65.44
## Mean : 74.18 Mean : 64.69
## 3rd Qu.: 81.52 3rd Qu.: 72.64
## Max. :100.00 Max. :100.00
## NA's :8425 NA's :1
## expectedFamContrib
## Min. : 0.000
## 1st Qu.: 1.351
## Median : 9.965
## Mean : 18.078
## 3rd Qu.: 25.156
## Max. :100.000
## NA's :436#add totalAwardWVU, totalAwardnonWVU to our finDataWVU table
totalAwardWVU -> finDataTableWVU$totalAwardWVU
totalAwardnonWVU -> finDataTableWVU$totalAwardnonWVU
totalAwardScholar -> finDataTableWVU$totalAwardPromScholar
summary(finDataTableWVU)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0 Median : 0.0 Median : 0.0 Median : 0.0
## Mean : 950 Mean : 189.3 Mean : 526.6 Mean : 301.2
## 3rd Qu.: 0 3rd Qu.: 0.0 3rd Qu.: 0.0 3rd Qu.: 0.0
## Max. :21336 Max. :17233.0 Max. :15603.0 Max. :41170.0
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:3922 White :3435
## 1st Qu.: 0.0 M:4668 Black : 446
## Median : 0.0 Hispanic: 79
## Mean : 187.8 Asian : 106
## 3rd Qu.: 0.0 Native : 16
## Max. :9338.0 Unknown :4464
## NA's : 44
## degreeF degreeType
## Bachelor of Science :3430 Bachelor Degree :7531
## Bachelor of Arts :2040 Regent Degree : 3
## Associate of Arts : 847 Degree Not Declared : 111
## BS in Business Administration : 797 Associate Arts : 847
## BS in Journalism : 238 Associate Applied Sci: 98
## Bachelor of Multidisc. Studies: 150
## (Other) :1088
## studentLoc stateIndicator proxStudentType
## WV :4341 Out-of-State:4249 Res or Out-of-State:6834
## PA : 935 In-State :4341 Long Commute : 227
## MD : 778 Short Commute :1529
## VA : 673
## NJ : 473
## OH : 302
## (Other):1088
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 1.00 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.: 58.97 1st Qu.: 73.27 1st Qu.: 45.50 1st Qu.: 45.00
## Median : 73.43 Median : 85.64 Median : 54.59 Median : 52.62
## Mean : 71.21 Mean : 82.45 Mean : 55.49 Mean : 53.08
## 3rd Qu.: 84.87 3rd Qu.: 95.79 3rd Qu.: 64.58 3rd Qu.: 60.23
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :100.00
## NA's :145 NA's :3510 NA's :2074 NA's :1793
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 1.00 Min. : 13.60 Some Affinity:3718
## 1st Qu.: 68.32 1st Qu.: 57.17 No Affinity :4872
## Median : 73.60 Median : 65.44
## Mean : 74.18 Mean : 64.69
## 3rd Qu.: 81.52 3rd Qu.: 72.64
## Max. :100.00 Max. :100.00
## NA's :8425 NA's :1
## expectedFamContrib totalAwardWVU totalAwardnonWVU
## Min. : 0.000 Min. : 0.0 Min. : 0
## 1st Qu.: 1.351 1st Qu.: 0.0 1st Qu.: 0
## Median : 9.965 Median : 447.5 Median : 5444
## Mean : 18.078 Mean : 2154.9 Mean : 7746
## 3rd Qu.: 25.156 3rd Qu.: 3000.0 3rd Qu.:12645
## Max. :100.000 Max. :43560.0 Max. :44595
## NA's :436
## totalAwardPromScholar
## Min. : 0.0
## 1st Qu.: 0.0
## Median : 0.0
## Mean : 874.1
## 3rd Qu.: 0.0
## Max. :7125.0
## names(finDataTableWVU)## [1] "rule49Grant" "instEmployAid"
## [3] "instGrantAcademic" "instGrantAthletic"
## [5] "instGrantOther" "studentGender"
## [7] "studentEthn" "degreeF"
## [9] "degreeType" "studentLoc"
## [11] "stateIndicator" "proxStudentType"
## [13] "highSchoolGPA" "prevColGPA"
## [15] "highestACT" "totalSAT"
## [17] "scoreGED" "scaledAcademAchiev"
## [19] "affinityStatus" "expectedFamContrib"
## [21] "totalAwardWVU" "totalAwardnonWVU"
## [23] "totalAwardPromScholar"#Identify subset of students that received WVU aid, Other aid, are Promise students
aidStudentWVU <- factor(finDataTableWVU$totalAwardWVU > 0, labels = c("Did not received WVU aid", "Received WVU aid"))
aidStudentnonWVU <- factor(finDataTableWVU$totalAwardnonWVU > 0, labels = c("Did not received other aid", "Received other aid"))
aidStudentPromScholar <- factor(finDataTableWVU$totalAwardPromScholar > 0, labels = c("Is not Promise", "Is Promise"))
aidStudentWVU -> finDataTableWVU$aidStudentWVU
aidStudentnonWVU -> finDataTableWVU$aidStudentnonWVU
aidStudentPromScholar -> finDataTableWVU$aidStudentPromScholar
#create new table with only students that have been awarded > 4000
finDataTableWVU_AL1 <- subset(finDataTableWVU, totalAwardWVU > 40000)
summary(finDataTableWVU_AL1)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. :0 Min. :0 Min. : 0 Min. :38293
## 1st Qu.:0 1st Qu.:0 1st Qu.: 0 1st Qu.:40037
## Median :0 Median :0 Median :3000 Median :40308
## Mean :0 Mean :0 Mean :1800 Mean :40074
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:3000 3rd Qu.:40560
## Max. :0 Max. :0 Max. :3000 Max. :41170
##
## instGrantOther studentGender studentEthn
## Min. :0 F:1 White :1
## 1st Qu.:0 M:4 Black :0
## Median :0 Hispanic:0
## Mean :0 Asian :0
## 3rd Qu.:0 Native :0
## Max. :0 Unknown :4
##
## degreeF degreeType studentLoc
## Bachelor of Science :3 Bachelor Degree :5 WV :4
## Bachelor of Arts :1 Regent Degree :0 GA :1
## BS in Business Administration:1 Degree Not Declared :0 AE :0
## Associate of Applied Sci :0 Associate Arts :0 AK :0
## Associate of Arts :0 Associate Applied Sci:0 AL :0
## Bachelor Electronic Engr :0 AP :0
## (Other) :0 (Other):0
## stateIndicator proxStudentType highSchoolGPA
## Out-of-State:1 Res or Out-of-State:1 Min. :55.88
## In-State :4 Long Commute :0 1st Qu.:66.91
## Short Commute :4 Median :71.75
## Mean :69.45
## 3rd Qu.:75.25
## Max. :77.47
##
## prevColGPA highestACT totalSAT scoreGED
## Min. :87.62 Min. :42.78 Min. :42.46 Min. : NA
## 1st Qu.:87.62 1st Qu.:53.22 1st Qu.:52.62 1st Qu.: NA
## Median :87.62 Median :63.67 Median :57.69 Median : NA
## Mean :87.62 Mean :59.73 Mean :57.35 Mean :NaN
## 3rd Qu.:87.62 3rd Qu.:68.21 3rd Qu.:64.46 3rd Qu.: NA
## Max. :87.62 Max. :72.75 Max. :69.54 Max. : NA
## NA's :4 NA's :2 NA's :5
## scaledAcademAchiev affinityStatus expectedFamContrib
## Min. :62.58 Some Affinity:1 Min. : 0.000
## 1st Qu.:63.03 No Affinity :4 1st Qu.: 9.144
## Median :63.93 Median : 18.287
## Mean :64.53 Mean : 39.429
## 3rd Qu.:65.69 3rd Qu.: 59.144
## Max. :67.40 Max. :100.000
## NA's :2
## totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. :40037 Min. : 0 Min. :0
## 1st Qu.:41170 1st Qu.: 0 1st Qu.:0
## Median :41293 Median : 0 Median :0
## Mean :41874 Mean :1129 Mean :0
## 3rd Qu.:43308 3rd Qu.: 0 3rd Qu.:0
## Max. :43560 Max. :5645 Max. :0
##
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid:0 Did not received other aid:4
## Received WVU aid :5 Received other aid :1
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:5
## Is Promise :0
##
##
##
##
## #AL2
finDataTableWVU_AL2 <- subset(finDataTableWVU, totalAwardWVU > 20000 & totalAwardWVU <= 40000)
summary(finDataTableWVU_AL2)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0 Min. : 0 Min. : 0
## 1st Qu.: 0 1st Qu.: 0 1st Qu.: 0 1st Qu.:10846
## Median : 0 Median : 0 Median : 0 Median :26770
## Mean : 4030 Mean : 1712 Mean : 1170 Mean :22643
## 3rd Qu.: 7562 3rd Qu.: 170 3rd Qu.: 3000 3rd Qu.:35444
## Max. :21336 Max. :17233 Max. :11938 Max. :39812
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:39 White :23
## 1st Qu.: 0.0 M:38 Black :14
## Median : 0.0 Hispanic: 0
## Mean : 458.9 Asian : 2
## 3rd Qu.: 0.0 Native : 1
## Max. :9338.0 Unknown :37
##
## degreeF degreeType
## Bachelor of Arts :32 Bachelor Degree :77
## Bachelor of Science :30 Regent Degree : 0
## BS in Business Administration: 5 Degree Not Declared : 0
## Bachelor of Fine Arts : 2 Associate Arts : 0
## BS in Aerospace Engineering : 2 Associate Applied Sci: 0
## BS in Journalism : 2
## (Other) : 4
## studentLoc stateIndicator proxStudentType
## WV :35 Out-of-State:42 Res or Out-of-State:43
## PA : 7 In-State :35 Long Commute : 0
## GA : 5 Short Commute :34
## TX : 4
## MD : 3
## FL : 2
## (Other):21
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 21.98 Min. : 51.24 Min. :23.71 Min. :23.85
## 1st Qu.: 62.34 1st Qu.: 69.19 1st Qu.:41.87 1st Qu.:43.94
## Median : 73.10 Median : 86.02 Median :56.40 Median :55.15
## Mean : 72.42 Mean : 82.17 Mean :56.33 Mean :56.11
## 3rd Qu.: 88.57 3rd Qu.: 96.53 3rd Qu.:67.76 3rd Qu.:67.85
## Max. :100.00 Max. :100.00 Max. :84.56 Max. :95.77
## NA's :1 NA's :31 NA's :26 NA's :9
## scoreGED scaledAcademAchiev affinityStatus
## Min. :72.28 Min. :31.59 Some Affinity:30
## 1st Qu.:72.28 1st Qu.:57.53 No Affinity :47
## Median :72.28 Median :67.04
## Mean :72.28 Mean :65.54
## 3rd Qu.:72.28 3rd Qu.:75.57
## Max. :72.28 Max. :87.51
## NA's :76
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. :20191 Min. : 0 Min. :0
## 1st Qu.: 0.000 1st Qu.:23520 1st Qu.: 0 1st Qu.:0
## Median : 2.321 Median :30346 Median : 0 Median :0
## Mean : 12.848 Mean :30014 Mean : 2388 Mean :0
## 3rd Qu.: 17.799 3rd Qu.:36555 3rd Qu.: 5444 3rd Qu.:0
## Max. :100.000 Max. :39812 Max. :11339 Max. :0
## NA's :11
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid:45
## Received WVU aid :77 Received other aid :32
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:77
## Is Promise : 0
##
##
##
##
## #AL3
finDataTableWVU_AL3 <- subset(finDataTableWVU, totalAwardWVU > 10000 & totalAwardWVU <= 20000)
summary(finDataTableWVU_AL3)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0 Min. : 0 Min. : 0
## 1st Qu.: 800 1st Qu.: 0 1st Qu.: 0 1st Qu.: 0
## Median : 8336 Median : 0 Median : 0 Median : 0
## Mean : 7239 Mean : 2358 Mean : 1799 Mean : 1425
## 3rd Qu.:12500 3rd Qu.: 2040 3rd Qu.: 3000 3rd Qu.: 0
## Max. :18000 Max. :14982 Max. :15603 Max. :19771
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:116 White : 75
## 1st Qu.: 0.0 M:140 Black : 21
## Median : 0.0 Hispanic: 4
## Mean : 744.4 Asian : 3
## 3rd Qu.: 0.0 Native : 1
## Max. :9338.0 Unknown :151
## NA's : 1
## degreeF degreeType
## Bachelor of Science :108 Bachelor Degree :251
## Bachelor of Arts : 54 Regent Degree : 0
## BS in Business Administration: 21 Degree Not Declared : 0
## BS in Mechanical Engineering : 10 Associate Arts : 5
## Bachelor of Music : 8 Associate Applied Sci: 0
## BS in Chemical Engineering : 6
## (Other) : 49
## studentLoc stateIndicator proxStudentType
## WV :72 Out-of-State:184 Res or Out-of-State:209
## PA :47 In-State : 72 Long Commute : 3
## MD :35 Short Commute : 44
## VA :21
## OH :17
## FR : 8
## (Other):56
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 14.18 Min. : 31.94 Min. :19.17 Min. :11.15
## 1st Qu.: 73.10 1st Qu.: 75.25 1st Qu.:50.95 1st Qu.:51.77
## Median : 79.49 Median : 86.76 Median :61.85 Median :65.31
## Mean : 79.49 Mean : 84.34 Mean :62.66 Mean :63.98
## 3rd Qu.: 91.63 3rd Qu.: 96.91 3rd Qu.:79.11 3rd Qu.:77.15
## Max. :100.00 Max. :100.00 Max. :99.09 Max. :95.77
## NA's :5 NA's :92 NA's :72 NA's :32
## scoreGED scaledAcademAchiev affinityStatus
## Min. :72.28 Min. :23.03 Some Affinity:109
## 1st Qu.:78.22 1st Qu.:66.62 No Affinity :147
## Median :80.86 Median :72.78
## Mean :79.54 Mean :72.43
## 3rd Qu.:82.18 3rd Qu.:79.80
## Max. :84.16 Max. :95.78
## NA's :252
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. :10005 Min. : 0 Min. : 0.0
## 1st Qu.: 3.469 1st Qu.:11697 1st Qu.: 0 1st Qu.: 0.0
## Median : 12.600 Median :12902 Median : 4750 Median : 0.0
## Mean : 18.589 Mean :13565 Mean : 5869 Mean : 610.6
## 3rd Qu.: 25.107 3rd Qu.:15500 3rd Qu.:10274 3rd Qu.: 0.0
## Max. :100.000 Max. :20000 Max. :22603 Max. :4750.0
## NA's :21
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid: 93
## Received WVU aid :256 Received other aid :163
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:223
## Is Promise : 33
##
##
##
##
## #AL4
finDataTableWVU_AL4 <- subset(finDataTableWVU, totalAwardWVU > 5000 & totalAwardWVU <= 10000)
summary(finDataTableWVU_AL4)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0 1st Qu.: 0.0
## Median : 4000 Median : 0.0 Median : 0 Median : 0.0
## Mean : 3705 Mean : 612.7 Mean :1439 Mean : 333.3
## 3rd Qu.: 6000 3rd Qu.: 0.0 3rd Qu.:3000 3rd Qu.: 0.0
## Max. :10000 Max. :9258.0 Max. :9600 Max. :9088.0
##
## instGrantOther studentGender studentEthn
## Min. : 0 F:281 White :209
## 1st Qu.: 0 M:346 Black : 31
## Median : 0 Hispanic: 3
## Mean :1045 Asian : 8
## 3rd Qu.:2000 Native : 0
## Max. :7392 Unknown :372
## NA's : 4
## degreeF degreeType
## Bachelor of Science :300 Bachelor Degree :599
## Bachelor of Arts :127 Regent Degree : 0
## BS in Business Administration: 55 Degree Not Declared : 6
## Associate of Arts : 20 Associate Arts : 20
## BS in Journalism : 20 Associate Applied Sci: 2
## Bachelor of Music : 14
## (Other) : 91
## studentLoc stateIndicator proxStudentType
## WV :223 Out-of-State:404 Res or Out-of-State:494
## PA :118 In-State :223 Long Commute : 15
## MD : 57 Short Commute :118
## VA : 50
## NJ : 37
## OH : 27
## (Other):115
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 15.26 Min. : 1.00 Min. : 10.99 Min. :19.62
## 1st Qu.: 69.26 1st Qu.: 75.00 1st Qu.: 50.95 1st Qu.:51.77
## Median : 76.60 Median : 86.64 Median : 62.76 Median :60.23
## Mean : 76.34 Mean : 83.81 Mean : 62.22 Mean :59.29
## 3rd Qu.: 87.56 3rd Qu.: 96.29 3rd Qu.: 73.66 3rd Qu.:68.69
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :94.92
## NA's :19 NA's :264 NA's :141 NA's :87
## scoreGED scaledAcademAchiev affinityStatus
## Min. :63.04 Min. :29.35 Some Affinity:243
## 1st Qu.:69.64 1st Qu.:63.29 No Affinity :384
## Median :73.60 Median :70.57
## Mean :76.14 Mean :69.42
## 3rd Qu.:80.20 3rd Qu.:76.47
## Max. :94.72 Max. :98.31
## NA's :614
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. : 5025 Min. : 0 Min. : 0
## 1st Qu.: 2.281 1st Qu.: 6000 1st Qu.: 653 1st Qu.: 0
## Median : 9.772 Median : 6903 Median : 6434 Median : 0
## Mean : 18.779 Mean : 7135 Mean : 8578 Mean : 922
## 3rd Qu.: 27.067 3rd Qu.: 8422 3rd Qu.:13458 3rd Qu.: 0
## Max. :100.000 Max. :10000 Max. :33239 Max. :4750
## NA's :14
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid:151
## Received WVU aid :627 Received other aid :476
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:505
## Is Promise :122
##
##
##
##
## #AL5
finDataTableWVU_AL5 <- subset(finDataTableWVU, totalAwardWVU > 1000 & totalAwardWVU <= 5000)
summary(finDataTableWVU_AL5)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0 Min. : 0.00
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0 1st Qu.: 0.00
## Median : 0 Median : 0.0 Median : 0 Median : 0.00
## Mean :1420 Mean : 184.7 Mean :1060 Mean : 27.01
## 3rd Qu.:3000 3rd Qu.: 0.0 3rd Qu.:2000 3rd Qu.: 0.00
## Max. :5000 Max. :4996.0 Max. :5000 Max. :4866.00
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:1111 White : 913
## 1st Qu.: 0.0 M:1390 Black : 79
## Median : 0.0 Hispanic: 21
## Mean : 244.9 Asian : 28
## 3rd Qu.: 0.0 Native : 4
## Max. :5000.0 Unknown :1446
## NA's : 10
## degreeF degreeType
## Bachelor of Science :1133 Bachelor Degree :2329
## Bachelor of Arts : 578 Regent Degree : 0
## BS in Business Administration: 241 Degree Not Declared : 22
## Associate of Arts : 142 Associate Arts : 142
## BS in Journalism : 71 Associate Applied Sci: 8
## Bachelor of Music : 36
## (Other) : 300
## studentLoc stateIndicator proxStudentType
## WV :1327 Out-of-State:1174 Res or Out-of-State:1970
## PA : 327 In-State :1327 Long Commute : 62
## MD : 214 Short Commute : 469
## VA : 169
## NJ : 136
## OH : 106
## (Other): 222
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 8.264 Min. : 1.00 Min. :11.90 Min. : 1.00
## 1st Qu.: 69.062 1st Qu.: 75.25 1st Qu.:50.95 1st Qu.: 50.92
## Median : 78.142 Median : 87.13 Median :59.13 Median : 56.00
## Mean : 77.291 Mean : 83.91 Mean :59.25 Mean : 55.95
## 3rd Qu.: 88.903 3rd Qu.: 96.53 3rd Qu.:67.30 3rd Qu.: 62.77
## Max. :100.000 Max. :100.00 Max. :97.28 Max. :100.00
## NA's :39 NA's :973 NA's :493 NA's :435
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 61.72 Min. : 23.36 Some Affinity:1107
## 1st Qu.: 67.99 1st Qu.: 62.47 No Affinity :1394
## Median : 77.56 Median : 69.09
## Mean : 78.31 Mean : 68.55
## 3rd Qu.: 86.47 3rd Qu.: 75.07
## Max. :100.00 Max. :100.00
## NA's :2471
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. :1004 Min. : 0 Min. : 0
## 1st Qu.: 3.889 1st Qu.:2000 1st Qu.: 2420 1st Qu.: 0
## Median : 14.668 Median :3000 Median : 5880 Median : 0
## Mean : 22.274 Mean :2937 Mean : 8504 Mean :1777
## 3rd Qu.: 31.640 3rd Qu.:4000 3rd Qu.:13245 3rd Qu.:4750
## Max. :100.000 Max. :5000 Max. :42328 Max. :7125
## NA's :73
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid: 548
## Received WVU aid :2501 Received other aid :1953
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:1541
## Is Promise : 960
##
##
##
##
## #AL6
finDataTableWVU_AL6 <- subset(finDataTableWVU, totalAwardWVU > 500 & totalAwardWVU <= 1000)
summary(finDataTableWVU_AL6)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0.0 Min. : 0.00 Min. : 0 Min. : 0.00
## 1st Qu.: 0.0 1st Qu.: 0.00 1st Qu.: 0 1st Qu.: 0.00
## Median : 0.0 Median : 0.00 Median : 800 Median : 0.00
## Mean : 183.2 Mean : 54.13 Mean : 551 Mean : 3.46
## 3rd Qu.: 0.0 3rd Qu.: 0.00 3rd Qu.:1000 3rd Qu.: 0.00
## Max. :1000.0 Max. :959.00 Max. :1000 Max. :1000.00
##
## instGrantOther studentGender studentEthn
## Min. : 0 F:342 White :266
## 1st Qu.: 0 M:236 Black : 16
## Median : 0 Hispanic: 3
## Mean : 153 Asian : 3
## 3rd Qu.: 0 Native : 2
## Max. :1000 Unknown :286
## NA's : 2
## degreeF degreeType
## Bachelor of Science :216 Bachelor Degree :453
## Bachelor of Arts :117 Regent Degree : 0
## Associate of Arts : 99 Degree Not Declared : 14
## BS in Business Administration: 41 Associate Arts : 99
## BS in Journalism : 17 Associate Applied Sci: 12
## Degree Not Declared : 14
## (Other) : 74
## studentLoc stateIndicator proxStudentType
## WV :421 Out-of-State:157 Res or Out-of-State:460
## MD : 39 In-State :421 Long Commute : 28
## VA : 39 Short Commute : 90
## OH : 24
## PA : 21
## NY : 8
## (Other): 26
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 31.40 Min. : 32.19 Min. :15.53 Min. :12.85
## 1st Qu.: 70.41 1st Qu.: 75.25 1st Qu.:47.32 1st Qu.:42.46
## Median : 81.50 Median : 86.14 Median :51.86 Median :50.08
## Mean : 78.58 Mean : 83.27 Mean :51.89 Mean :50.45
## 3rd Qu.: 90.50 3rd Qu.: 94.31 3rd Qu.:55.50 3rd Qu.:56.85
## Max. :100.00 Max. :100.00 Max. :85.47 Max. :89.85
## NA's :12 NA's :197 NA's :106 NA's :136
## scoreGED scaledAcademAchiev affinityStatus
## Min. :73.60 Min. : 31.40 Some Affinity:252
## 1st Qu.:75.58 1st Qu.: 60.61 No Affinity :326
## Median :76.90 Median : 66.90
## Mean :78.06 Mean : 66.05
## 3rd Qu.:80.86 3rd Qu.: 72.36
## Max. :84.16 Max. :100.00
## NA's :570
## expectedFamContrib totalAwardWVU totalAwardnonWVU
## Min. : 0.000 Min. : 504.0 Min. : 0
## 1st Qu.: 1.358 1st Qu.:1000.0 1st Qu.: 4750
## Median : 7.347 Median :1000.0 Median : 8995
## Mean : 16.065 Mean : 944.7 Mean : 9562
## 3rd Qu.: 22.922 3rd Qu.:1000.0 3rd Qu.:13839
## Max. :100.000 Max. :1000.0 Max. :40333
## NA's :6
## totalAwardPromScholar aidStudentWVU
## Min. : 0 Did not received WVU aid: 0
## 1st Qu.: 0 Received WVU aid :578
## Median : 0
## Mean :1860
## 3rd Qu.:4750
## Max. :6980
##
## aidStudentnonWVU aidStudentPromScholar
## Did not received other aid: 59 Is not Promise:335
## Received other aid :519 Is Promise :243
##
##
##
##
## #AL7
finDataTableWVU_AL7 <- subset(finDataTableWVU, totalAwardWVU > 100 & totalAwardWVU <= 500)
summary(finDataTableWVU_AL7)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0.00 Min. : 0.00 Min. : 0.0 Min. : 0.000
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.: 0.000
## Median : 0.00 Median : 0.00 Median :400.0 Median : 0.000
## Mean : 48.24 Mean : 37.57 Mean :268.5 Mean : 1.173
## 3rd Qu.: 0.00 3rd Qu.: 0.00 3rd Qu.:500.0 3rd Qu.: 0.000
## Max. :500.00 Max. :498.00 Max. :500.0 Max. :400.000
##
## instGrantOther studentGender studentEthn
## Min. : 0.00 F:174 White :147
## 1st Qu.: 0.00 M:167 Black : 7
## Median : 0.00 Hispanic: 0
## Mean : 91.39 Asian : 7
## 3rd Qu.: 0.00 Native : 0
## Max. :500.00 Unknown :178
## NA's : 2
## degreeF degreeType
## Bachelor of Science :131 Bachelor Degree :296
## Bachelor of Arts : 78 Regent Degree : 1
## Associate of Arts : 34 Degree Not Declared : 8
## BS in Business Administration : 31 Associate Arts : 34
## Bachelor of Multidisc. Studies: 16 Associate Applied Sci: 2
## BS in Journalism : 10
## (Other) : 41
## studentLoc stateIndicator proxStudentType
## WV :239 Out-of-State:102 Res or Out-of-State:256
## MD : 27 In-State :239 Long Commute : 16
## PA : 18 Short Commute : 69
## VA : 14
## NJ : 11
## OH : 11
## (Other): 21
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 18.62 Min. : 41.59 Min. :20.98 Min. :12.85
## 1st Qu.: 69.06 1st Qu.: 76.24 1st Qu.:45.50 1st Qu.:44.15
## Median : 80.50 Median : 87.13 Median :52.77 Median :50.08
## Mean : 77.30 Mean : 84.20 Mean :52.87 Mean :51.23
## 3rd Qu.: 88.65 3rd Qu.: 95.79 3rd Qu.:59.13 3rd Qu.:58.54
## Max. :100.00 Max. :100.00 Max. :91.83 Max. :89.00
## NA's :5 NA's :96 NA's :52 NA's :85
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 69.64 Min. :35.94 Some Affinity:193
## 1st Qu.: 73.60 1st Qu.:60.56 No Affinity :148
## Median : 82.84 Median :67.03
## Mean : 82.69 Mean :66.57
## 3rd Qu.: 89.44 3rd Qu.:73.54
## Max. :100.00 Max. :97.15
## NA's :332
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. :130.0 Min. : 0 Min. : 0
## 1st Qu.: 1.368 1st Qu.:427.0 1st Qu.: 4701 1st Qu.: 0
## Median : 6.792 Median :500.0 Median : 6850 Median : 0
## Mean : 15.298 Mean :446.9 Mean : 8613 Mean :1717
## 3rd Qu.: 18.677 3rd Qu.:500.0 3rd Qu.:12963 3rd Qu.:4750
## Max. :100.000 Max. :500.0 Max. :41917 Max. :4750
## NA's :8
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid: 39
## Received WVU aid :341 Received other aid :302
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:204
## Is Promise :137
##
##
##
##
## #AL8
finDataTableWVU_AL8 <- subset(finDataTableWVU, totalAwardWVU > 0 & totalAwardWVU <= 100)
summary(finDataTableWVU_AL8)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. :0 Min. : 0.00 Min. : 0.00 Min. :0
## 1st Qu.:0 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:0
## Median :0 Median : 40.00 Median : 0.00 Median :0
## Mean :0 Mean : 36.82 Mean : 23.27 Mean :0
## 3rd Qu.:0 3rd Qu.: 58.00 3rd Qu.: 28.00 3rd Qu.:0
## Max. :0 Max. :100.00 Max. :100.00 Max. :0
##
## instGrantOther studentGender studentEthn
## Min. : 0.000 F:4 White :4
## 1st Qu.: 0.000 M:7 Black :1
## Median : 0.000 Hispanic:0
## Mean : 9.091 Asian :0
## 3rd Qu.: 0.000 Native :0
## Max. :100.000 Unknown :6
##
## degreeF degreeType studentLoc
## Bachelor of Science :4 Bachelor Degree :8 NJ :3
## Bachelor of Arts :3 Regent Degree :0 WV :3
## Associate of Arts :2 Degree Not Declared :0 PA :2
## Associate of Applied Sci :1 Associate Arts :2 MD :1
## BS in Business Administration:1 Associate Applied Sci:1 OH :1
## Bachelor Electronic Engr :0 VA :1
## (Other) :0 (Other):0
## stateIndicator proxStudentType highSchoolGPA
## Out-of-State:8 Res or Out-of-State:11 Min. :32.74
## In-State :3 Long Commute : 0 1st Qu.:45.56
## Short Commute : 0 Median :65.03
## Mean :64.57
## 3rd Qu.:80.50
## Max. :96.64
##
## prevColGPA highestACT totalSAT scoreGED
## Min. : 57.92 Min. :38.24 Min. :33.15 Min. : NA
## 1st Qu.: 85.64 1st Qu.:45.50 1st Qu.:45.85 1st Qu.: NA
## Median : 92.08 Median :54.59 Median :50.08 Median : NA
## Mean : 87.13 Mean :53.78 Mean :51.68 Mean :NaN
## 3rd Qu.:100.00 3rd Qu.:58.22 3rd Qu.:56.00 3rd Qu.: NA
## Max. :100.00 Max. :75.48 Max. :77.15 Max. : NA
## NA's :6 NA's :2 NA's :2 NA's :11
## scaledAcademAchiev affinityStatus expectedFamContrib
## Min. :44.75 Some Affinity:4 Min. : 0.009
## 1st Qu.:55.71 No Affinity :7 1st Qu.: 1.610
## Median :60.66 Median : 5.753
## Mean :62.10 Mean :11.133
## 3rd Qu.:68.76 3rd Qu.: 9.827
## Max. :81.35 Max. :39.594
## NA's :1
## totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 25.00 Min. : 0 Min. : 0.0
## 1st Qu.: 57.00 1st Qu.: 4264 1st Qu.: 0.0
## Median : 58.00 Median : 9339 Median : 0.0
## Mean : 69.18 Mean : 9915 Mean : 735.1
## 3rd Qu.:100.00 3rd Qu.:16966 3rd Qu.: 0.0
## Max. :100.00 Max. :19740 Max. :4750.0
##
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid:3
## Received WVU aid :11 Received other aid :8
##
##
##
##
##
## aidStudentPromScholar
## Is not Promise:9
## Is Promise :2
##
##
##
##
## #Descriptive stats
#create a function to summarize mean of the data
summaryTable <- function(a = NULL, table1 = NULL, list1 = list(studentGender), func = mean) {
table1 <- tapply(a, list1, func)
print(table1)
}
#Student attributes
#studentGender, studentEthn, degreeF, degreeType, studentLoc, stateIndicator, proxStudentType
for(i in 13:15){
print(colnames(finDataTableWVU[i]))
summaryTable(finDataTableWVU[,i], list1, func = mean)
writeLines("")
}## [1] "highSchoolGPA"
## F M
## NA NA
##
## [1] "prevColGPA"
## F M
## NA NA
##
## [1] "highestACT"
## F M
## NA NAnames(finDataTableWVU)## [1] "rule49Grant" "instEmployAid"
## [3] "instGrantAcademic" "instGrantAthletic"
## [5] "instGrantOther" "studentGender"
## [7] "studentEthn" "degreeF"
## [9] "degreeType" "studentLoc"
## [11] "stateIndicator" "proxStudentType"
## [13] "highSchoolGPA" "prevColGPA"
## [15] "highestACT" "totalSAT"
## [17] "scoreGED" "scaledAcademAchiev"
## [19] "affinityStatus" "expectedFamContrib"
## [21] "totalAwardWVU" "totalAwardnonWVU"
## [23] "totalAwardPromScholar" "aidStudentWVU"
## [25] "aidStudentnonWVU" "aidStudentPromScholar"summary(finDataTableWVU)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0 Median : 0.0 Median : 0.0 Median : 0.0
## Mean : 950 Mean : 189.3 Mean : 526.6 Mean : 301.2
## 3rd Qu.: 0 3rd Qu.: 0.0 3rd Qu.: 0.0 3rd Qu.: 0.0
## Max. :21336 Max. :17233.0 Max. :15603.0 Max. :41170.0
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:3922 White :3435
## 1st Qu.: 0.0 M:4668 Black : 446
## Median : 0.0 Hispanic: 79
## Mean : 187.8 Asian : 106
## 3rd Qu.: 0.0 Native : 16
## Max. :9338.0 Unknown :4464
## NA's : 44
## degreeF degreeType
## Bachelor of Science :3430 Bachelor Degree :7531
## Bachelor of Arts :2040 Regent Degree : 3
## Associate of Arts : 847 Degree Not Declared : 111
## BS in Business Administration : 797 Associate Arts : 847
## BS in Journalism : 238 Associate Applied Sci: 98
## Bachelor of Multidisc. Studies: 150
## (Other) :1088
## studentLoc stateIndicator proxStudentType
## WV :4341 Out-of-State:4249 Res or Out-of-State:6834
## PA : 935 In-State :4341 Long Commute : 227
## MD : 778 Short Commute :1529
## VA : 673
## NJ : 473
## OH : 302
## (Other):1088
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 1.00 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.: 58.97 1st Qu.: 73.27 1st Qu.: 45.50 1st Qu.: 45.00
## Median : 73.43 Median : 85.64 Median : 54.59 Median : 52.62
## Mean : 71.21 Mean : 82.45 Mean : 55.49 Mean : 53.08
## 3rd Qu.: 84.87 3rd Qu.: 95.79 3rd Qu.: 64.58 3rd Qu.: 60.23
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :100.00
## NA's :145 NA's :3510 NA's :2074 NA's :1793
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 1.00 Min. : 13.60 Some Affinity:3718
## 1st Qu.: 68.32 1st Qu.: 57.17 No Affinity :4872
## Median : 73.60 Median : 65.44
## Mean : 74.18 Mean : 64.69
## 3rd Qu.: 81.52 3rd Qu.: 72.64
## Max. :100.00 Max. :100.00
## NA's :8425 NA's :1
## expectedFamContrib totalAwardWVU totalAwardnonWVU
## Min. : 0.000 Min. : 0.0 Min. : 0
## 1st Qu.: 1.351 1st Qu.: 0.0 1st Qu.: 0
## Median : 9.965 Median : 447.5 Median : 5444
## Mean : 18.078 Mean : 2154.9 Mean : 7746
## 3rd Qu.: 25.156 3rd Qu.: 3000.0 3rd Qu.:12645
## Max. :100.000 Max. :43560.0 Max. :44595
## NA's :436
## totalAwardPromScholar aidStudentWVU
## Min. : 0.0 Did not received WVU aid:4194
## 1st Qu.: 0.0 Received WVU aid :4396
## Median : 0.0
## Mean : 874.1
## 3rd Qu.: 0.0
## Max. :7125.0
##
## aidStudentnonWVU aidStudentPromScholar
## Did not received other aid:2756 Is not Promise:6945
## Received other aid :5834 Is Promise :1645
##
##
##
##
## Now deal with the blank values and NA’s on variables within the finDataTableWVU dataset so that we can model these without excluding too many.
finDataTableWVU$highSchoolGPA.NA <- is.na(finDataTableWVU$highSchoolGPA)
finDataTableWVU$prevColGPA.NA <- is.na(finDataTableWVU$prevColGPA)
finDataTableWVU$highestACT.NA <- is.na(finDataTableWVU$highestACT)
finDataTableWVU$totalSAT.NA <- is.na(finDataTableWVU$totalSAT)
finDataTableWVU$scoreGED.NA <- is.na(finDataTableWVU$scoreGED)
finDataTableWVU$expectedFamContrib.NA <- is.na(finDataTableWVU$expectedFamContrib)
finDataTableWVU$studentEthn.NA <-is.na(finDataTableWVU$studentEthn)
finDataTableWVU$scaledAcademAchiev.NA <-is.na(finDataTableWVU$scaledAcademAchiev)
finDataTableWVU$highSchoolGPA[is.na(finDataTableWVU$highSchoolGPA)] = 1
finDataTableWVU$prevColGPA[is.na(finDataTableWVU$prevColGPA)] = 1
finDataTableWVU$highestACT[is.na(finDataTableWVU$highestACT)] = 1
finDataTableWVU$totalSAT[is.na(finDataTableWVU$totalSAT)] = 1
finDataTableWVU$scoreGED[is.na(finDataTableWVU$scoreGED)] = 1
finDataTableWVU$expectedFamContrib[is.na(finDataTableWVU$expectedFamContrib)] = 1
finDataTableWVU$studentEthn[is.na(finDataTableWVU$studentEthn)] = "Unknown"
finDataTableWVU$scaledAcademAchiev[is.na(finDataTableWVU$scaledAcademAchiev)] = 1
summary(finDataTableWVU)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0 Median : 0.0 Median : 0.0 Median : 0.0
## Mean : 950 Mean : 189.3 Mean : 526.6 Mean : 301.2
## 3rd Qu.: 0 3rd Qu.: 0.0 3rd Qu.: 0.0 3rd Qu.: 0.0
## Max. :21336 Max. :17233.0 Max. :15603.0 Max. :41170.0
##
## instGrantOther studentGender studentEthn
## Min. : 0.0 F:3922 White :3435
## 1st Qu.: 0.0 M:4668 Black : 446
## Median : 0.0 Hispanic: 79
## Mean : 187.8 Asian : 106
## 3rd Qu.: 0.0 Native : 16
## Max. :9338.0 Unknown :4508
##
## degreeF degreeType
## Bachelor of Science :3430 Bachelor Degree :7531
## Bachelor of Arts :2040 Regent Degree : 3
## Associate of Arts : 847 Degree Not Declared : 111
## BS in Business Administration : 797 Associate Arts : 847
## BS in Journalism : 238 Associate Applied Sci: 98
## Bachelor of Multidisc. Studies: 150
## (Other) :1088
## studentLoc stateIndicator proxStudentType
## WV :4341 Out-of-State:4249 Res or Out-of-State:6834
## PA : 935 In-State :4341 Long Commute : 227
## MD : 778 Short Commute :1529
## VA : 673
## NJ : 473
## OH : 302
## (Other):1088
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 1.00 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.: 58.03 1st Qu.: 1.00 1st Qu.: 24.61 1st Qu.: 34.00
## Median : 73.10 Median : 65.84 Median : 50.05 Median : 49.23
## Mean : 70.03 Mean : 49.17 Mean : 42.34 Mean : 42.21
## 3rd Qu.: 84.53 3rd Qu.: 88.86 3rd Qu.: 60.94 3rd Qu.: 58.54
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :100.00
##
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 1.000 Min. : 1.00 Some Affinity:3718
## 1st Qu.: 1.000 1st Qu.: 57.16 No Affinity :4872
## Median : 1.000 Median : 65.43
## Mean : 2.406 Mean : 64.68
## 3rd Qu.: 1.000 3rd Qu.: 72.64
## Max. :100.000 Max. :100.00
##
## expectedFamContrib totalAwardWVU totalAwardnonWVU
## Min. : 0.000 Min. : 0.0 Min. : 0
## 1st Qu.: 1.000 1st Qu.: 0.0 1st Qu.: 0
## Median : 8.654 Median : 447.5 Median : 5444
## Mean : 17.211 Mean : 2154.9 Mean : 7746
## 3rd Qu.: 24.163 3rd Qu.: 3000.0 3rd Qu.:12645
## Max. :100.000 Max. :43560.0 Max. :44595
##
## totalAwardPromScholar aidStudentWVU
## Min. : 0.0 Did not received WVU aid:4194
## 1st Qu.: 0.0 Received WVU aid :4396
## Median : 0.0
## Mean : 874.1
## 3rd Qu.: 0.0
## Max. :7125.0
##
## aidStudentnonWVU aidStudentPromScholar
## Did not received other aid:2756 Is not Promise:6945
## Received other aid :5834 Is Promise :1645
##
##
##
##
##
## highSchoolGPA.NA prevColGPA.NA highestACT.NA totalSAT.NA
## Mode :logical Mode :logical Mode :logical Mode :logical
## FALSE:8445 FALSE:5080 FALSE:6516 FALSE:6797
## TRUE :145 TRUE :3510 TRUE :2074 TRUE :1793
## NA's :0 NA's :0 NA's :0 NA's :0
##
##
##
## scoreGED.NA expectedFamContrib.NA studentEthn.NA
## Mode :logical Mode :logical Mode :logical
## FALSE:165 FALSE:8154 FALSE:8546
## TRUE :8425 TRUE :436 TRUE :44
## NA's :0 NA's :0 NA's :0
##
##
##
## scaledAcademAchiev.NA
## Mode :logical
## FALSE:8589
## TRUE :1
## NA's :0
##
##
## #model transformation
#To avoid problems with negative values of the response variable, we add 0.5 to all observations
pred <- finDataTableWVU$totalAwardWVU + 0.5
modWVUAid <- lm(sqrt(pred) ~ studentGender + studentEthn + degreeF + proxStudentType + affinityStatus + expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU + aidStudentWVU + aidStudentPromScholar + affinityStatus + highestACT + highestACT.NA + totalSAT + totalSAT.NA + totalAwardnonWVU + totalAwardPromScholar, data = finDataTableWVU)
require(MASS)## Loading required package: MASSbc <- boxcox(modWVUAid)
#The optimal transformation has a parameter close to -2
#find the approximate mle as the x-value that yields the maximum
bc$x[bc$y==max(bc$y)]## [1] -2#call the function with a single parameter value to just evaluate the log-likelihood
bc0 <- boxcox(modWVUAid, lambda = 1, plotit = TRUE) 
bc1 <- boxcox(modWVUAid, lambda = 0, plotit = TRUE) 
bc2 <- boxcox(modWVUAid, lambda = 2, plotit = TRUE) 
bc3 <- boxcox(modWVUAid, lambda = -1, plotit = TRUE)
bc4 <- boxcox(modWVUAid, lambda = -2, plotit = TRUE)
TukeyHSD(aov(modWVUAid), ordered = TRUE, conf.level = 0.99, "proxStudentType")## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## expectedFamContrib## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## expectedFamContrib.NA## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## highestACT## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## highestACT.NA## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## totalSAT## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## totalSAT.NA## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## totalAwardnonWVU## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## totalAwardPromScholar## Tukey multiple comparisons of means
## 99% family-wise confidence level
## factor levels have been ordered
##
## Fit: aov(formula = modWVUAid)
##
## $proxStudentType
## diff lwr upr p adj
## Res or Out-of-State-Long Commute 3.392833 -0.4377316 7.223397 0.0266593
## Short Commute-Long Commute 5.384912 1.3463602 9.423464 0.0003026
## Short Commute-Res or Out-of-State 1.992079 0.3858042 3.598354 0.0008842summary(modWVUAid)##
## Call:
## lm(formula = sqrt(pred) ~ studentGender + studentEthn + degreeF +
## proxStudentType + affinityStatus + expectedFamContrib + expectedFamContrib.NA +
## aidStudentnonWVU + aidStudentWVU + aidStudentPromScholar +
## affinityStatus + highestACT + highestACT.NA + totalSAT +
## totalSAT.NA + totalAwardnonWVU + totalAwardPromScholar, data = finDataTableWVU)
##
## Residuals:
## Min 1Q Median 3Q Max
## -58.876 -7.367 -1.087 4.828 143.313
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) -2.861e+01 2.429e+00 -11.780
## studentGenderM 1.914e-01 4.366e-01 0.438
## studentEthnBlack 8.897e+00 1.010e+00 8.810
## studentEthnHispanic 2.288e+00 2.223e+00 1.030
## studentEthnAsian 4.584e-01 1.936e+00 0.237
## studentEthnNative 4.875e+00 4.893e+00 0.996
## studentEthnUnknown 1.129e+00 4.583e-01 2.463
## degreeFAssociate of Arts 8.974e-01 2.086e+00 0.430
## degreeFBachelor Electronic Engr 8.001e+00 1.393e+01 0.575
## degreeFBachelor Engr Tech 2.263e+01 9.946e+00 2.275
## degreeFBachelor of Arts 6.042e+00 2.048e+00 2.950
## degreeFBachelor of Fine Arts 3.206e+00 2.716e+00 1.180
## degreeFBachelor of Multidisc. Studies 2.543e+00 2.562e+00 0.993
## degreeFBachelor of Music 1.446e+01 2.957e+00 4.890
## degreeFBachelor of Science 5.517e+00 2.032e+00 2.715
## degreeFBachelor of Science in Nursing 3.497e+00 5.759e+00 0.607
## degreeFBachelor of Social Work 3.321e+00 3.618e+00 0.918
## degreeFBS in Aerospace Engineering 9.394e+00 3.196e+00 2.939
## degreeFBS in Agriculture 1.374e+00 3.249e+00 0.423
## degreeFBS in Biometric Systems 4.005e+00 6.221e+00 0.644
## degreeFBS in Business Administration 4.875e+00 2.122e+00 2.297
## degreeFBS in Chemical Engineering 1.327e+01 3.389e+00 3.916
## degreeFBS in Civil Engineering 8.499e+00 3.339e+00 2.545
## degreeFBS in Computer Engineering 3.883e+00 4.141e+00 0.938
## degreeFBS in Computer Science 1.158e+01 3.259e+00 3.554
## degreeFBS in Electrical Engineering 9.398e+00 3.552e+00 2.646
## degreeFBS in Forestry 2.593e+00 3.673e+00 0.706
## degreeFBS in Industrial Engineering 1.195e+01 3.780e+00 3.162
## degreeFBS in Journalism 5.210e+00 2.374e+00 2.195
## degreeFBS in Landscape Architecture 4.541e+00 4.260e+00 1.066
## degreeFBS in Mechanical Engineering 1.324e+01 3.172e+00 4.173
## degreeFBS in Mining Engineering -4.911e+00 6.210e+00 -0.791
## degreeFBS in Petroleum & Natl Gas Eng 8.194e+00 3.621e+00 2.263
## degreeFBS in Physical Education 1.876e+01 5.131e+00 3.655
## degreeFBS in Recreation -1.652e+00 5.137e+00 -0.322
## degreeFDegree Not Declared 6.683e-01 2.710e+00 0.247
## degreeFRegents Bachelor of Arts -2.915e+00 1.143e+01 -0.255
## proxStudentTypeLong Commute -2.081e+00 1.330e+00 -1.564
## proxStudentTypeShort Commute 2.155e+00 5.707e-01 3.775
## affinityStatusNo Affinity 1.614e+00 4.346e-01 3.713
## expectedFamContrib -1.680e-02 9.906e-03 -1.696
## expectedFamContrib.NATRUE 1.877e+00 1.039e+00 1.806
## aidStudentnonWVUReceived other aid -4.953e-01 6.748e-01 -0.734
## aidStudentWVUReceived WVU aid 5.907e+01 4.775e-01 123.699
## aidStudentPromScholarIs Promise -3.396e+01 3.701e+00 -9.175
## highestACT 1.783e-01 1.810e-02 9.851
## highestACT.NATRUE 1.042e+01 1.088e+00 9.576
## totalSAT 2.819e-01 2.058e-02 13.699
## totalSAT.NATRUE 1.292e+01 1.190e+00 10.860
## totalAwardnonWVU -1.011e-04 3.493e-05 -2.895
## totalAwardPromScholar 4.542e-03 8.016e-04 5.667
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## studentGenderM 0.661120
## studentEthnBlack < 2e-16 ***
## studentEthnHispanic 0.303271
## studentEthnAsian 0.812841
## studentEthnNative 0.319197
## studentEthnUnknown 0.013786 *
## degreeFAssociate of Arts 0.666998
## degreeFBachelor Electronic Engr 0.565586
## degreeFBachelor Engr Tech 0.022913 *
## degreeFBachelor of Arts 0.003190 **
## degreeFBachelor of Fine Arts 0.237926
## degreeFBachelor of Multidisc. Studies 0.320904
## degreeFBachelor of Music 1.03e-06 ***
## degreeFBachelor of Science 0.006634 **
## degreeFBachelor of Science in Nursing 0.543676
## degreeFBachelor of Social Work 0.358740
## degreeFBS in Aerospace Engineering 0.003298 **
## degreeFBS in Agriculture 0.672459
## degreeFBS in Biometric Systems 0.519706
## degreeFBS in Business Administration 0.021645 *
## degreeFBS in Chemical Engineering 9.08e-05 ***
## degreeFBS in Civil Engineering 0.010930 *
## degreeFBS in Computer Engineering 0.348469
## degreeFBS in Computer Science 0.000382 ***
## degreeFBS in Electrical Engineering 0.008166 **
## degreeFBS in Forestry 0.480322
## degreeFBS in Industrial Engineering 0.001572 **
## degreeFBS in Journalism 0.028182 *
## degreeFBS in Landscape Architecture 0.286439
## degreeFBS in Mechanical Engineering 3.03e-05 ***
## degreeFBS in Mining Engineering 0.429073
## degreeFBS in Petroleum & Natl Gas Eng 0.023682 *
## degreeFBS in Physical Education 0.000258 ***
## degreeFBS in Recreation 0.747826
## degreeFDegree Not Declared 0.805233
## degreeFRegents Bachelor of Arts 0.798610
## proxStudentTypeLong Commute 0.117868
## proxStudentTypeShort Commute 0.000161 ***
## affinityStatusNo Affinity 0.000206 ***
## expectedFamContrib 0.089898 .
## expectedFamContrib.NATRUE 0.071016 .
## aidStudentnonWVUReceived other aid 0.463029
## aidStudentWVUReceived WVU aid < 2e-16 ***
## aidStudentPromScholarIs Promise < 2e-16 ***
## highestACT < 2e-16 ***
## highestACT.NATRUE < 2e-16 ***
## totalSAT < 2e-16 ***
## totalSAT.NATRUE < 2e-16 ***
## totalAwardnonWVU 0.003796 **
## totalAwardPromScholar 1.50e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 19.48 on 8539 degrees of freedom
## Multiple R-squared: 0.6987, Adjusted R-squared: 0.697
## F-statistic: 396.1 on 50 and 8539 DF, p-value: < 2.2e-16ncvTest(modWVUAid)## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 4194.659 Df = 1 p = 0plot(modWVUAid)
mmp(modWVUAid)
summary.aov(modWVUAid)## Df Sum Sq Mean Sq F value Pr(>F)
## studentGender 1 11 11 0.029 0.863919
## studentEthn 5 89740 17948 47.284 < 2e-16 ***
## degreeF 30 423187 14106 37.163 < 2e-16 ***
## proxStudentType 2 8225 4113 10.835 2.00e-05 ***
## affinityStatus 1 3232 3232 8.515 0.003532 **
## expectedFamContrib 1 33203 33203 87.473 < 2e-16 ***
## expectedFamContrib.NA 1 13185 13185 34.736 3.92e-09 ***
## aidStudentnonWVU 1 193383 193383 509.470 < 2e-16 ***
## aidStudentWVU 1 6470783 6470783 17047.363 < 2e-16 ***
## aidStudentPromScholar 1 134270 134270 353.736 < 2e-16 ***
## highestACT 1 4948 4948 13.034 0.000308 ***
## highestACT.NA 1 51116 51116 134.665 < 2e-16 ***
## totalSAT 1 29303 29303 77.199 < 2e-16 ***
## totalSAT.NA 1 47609 47609 125.427 < 2e-16 ***
## totalAwardnonWVU 1 2585 2585 6.809 0.009085 **
## totalAwardPromScholar 1 12189 12189 32.112 1.50e-08 ***
## Residuals 8539 3241206 380
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1plot(totalAwardWVU ~ modWVUAid$fitted.values)
#Other model approach:
totalAwardWVUMod3 <- lm(sqrt(totalAwardWVU) ~ studentGender + studentEthn + degreeF + degreeType + studentLoc + stateIndicator + proxStudentType + scaledAcademAchiev + affinityStatus + expectedFamContrib, data = finDataTableWVU)
summary(totalAwardWVUMod3)##
## Call:
## lm(formula = sqrt(totalAwardWVU) ~ studentGender + studentEthn +
## degreeF + degreeType + studentLoc + stateIndicator + proxStudentType +
## scaledAcademAchiev + affinityStatus + expectedFamContrib,
## data = finDataTableWVU)
##
## Residuals:
## Min 1Q Median 3Q Max
## -103.217 -24.549 -5.017 19.719 187.986
##
## Coefficients: (5 not defined because of singularities)
## Estimate Std. Error t value
## (Intercept) -73.18893 33.04051 -2.215
## studentGenderM -0.07648 0.73554 -0.104
## studentEthnBlack 9.94979 1.76711 5.631
## studentEthnHispanic -0.26017 3.76653 -0.069
## studentEthnAsian 0.56880 3.24972 0.175
## studentEthnNative 9.10260 8.22911 1.106
## studentEthnUnknown 4.42730 0.77710 5.697
## degreeFAssociate of Arts 4.88580 3.49915 1.396
## degreeFBachelor Electronic Engr 2.30242 23.38293 0.098
## degreeFBachelor Engr Tech 40.50860 16.72631 2.422
## degreeFBachelor of Arts 8.13814 3.44674 2.361
## degreeFBachelor of Fine Arts 3.82727 4.57410 0.837
## degreeFBachelor of Multidisc. Studies 4.70740 4.30769 1.093
## degreeFBachelor of Music 29.44563 4.96853 5.926
## degreeFBachelor of Science 10.01735 3.42204 2.927
## degreeFBachelor of Science in Nursing 14.38266 9.67316 1.487
## degreeFBachelor of Social Work -1.93530 6.11300 -0.317
## degreeFBS in Aerospace Engineering 9.50975 5.38567 1.766
## degreeFBS in Agriculture 2.45791 5.46400 0.450
## degreeFBS in Biometric Systems 10.32416 10.44014 0.989
## degreeFBS in Business Administration 7.37477 3.57521 2.063
## degreeFBS in Chemical Engineering 12.42549 5.70203 2.179
## degreeFBS in Civil Engineering 23.81915 5.61094 4.245
## degreeFBS in Computer Engineering 12.12923 6.95250 1.745
## degreeFBS in Computer Science 24.93995 5.46371 4.565
## degreeFBS in Electrical Engineering 16.08203 5.97627 2.691
## degreeFBS in Forestry 4.44258 6.20946 0.715
## degreeFBS in Industrial Engineering 10.66108 6.36184 1.676
## degreeFBS in Journalism 8.29489 3.99769 2.075
## degreeFBS in Landscape Architecture 18.36802 7.17340 2.561
## degreeFBS in Mechanical Engineering 22.00283 5.35739 4.107
## degreeFBS in Mining Engineering 3.66000 10.48486 0.349
## degreeFBS in Petroleum & Natl Gas Eng 11.67234 6.12169 1.907
## degreeFBS in Physical Education 37.88957 8.70572 4.352
## degreeFBS in Recreation -10.29167 8.63223 -1.192
## degreeFDegree Not Declared 7.48866 4.55802 1.643
## degreeFRegents Bachelor of Arts 7.05486 19.18867 0.368
## degreeTypeRegent Degree NA NA NA
## degreeTypeDegree Not Declared NA NA NA
## degreeTypeAssociate Arts NA NA NA
## degreeTypeAssociate Applied Sci NA NA NA
## studentLocAK -6.96882 46.34705 -0.150
## studentLocAL 18.84469 35.46334 0.531
## studentLocAP 30.85610 46.36522 0.666
## studentLocAR 12.22545 36.67811 0.333
## studentLocAZ -1.56243 40.15331 -0.039
## studentLocBC 89.46949 40.15434 2.228
## studentLocCA 38.33453 33.18032 1.155
## studentLocCO 47.99947 34.39953 1.395
## studentLocCT 20.64168 33.03076 0.625
## studentLocDC 21.89776 33.01180 0.663
## studentLocDE 22.80921 33.03766 0.690
## studentLocFL 44.18063 33.06616 1.336
## studentLocFR 89.49559 33.54924 2.668
## studentLocGA 57.33753 33.23487 1.725
## studentLocIA 6.79058 35.44057 0.192
## studentLocIL 39.93331 33.28116 1.200
## studentLocIN 69.77234 34.04008 2.050
## studentLocKS -11.79677 40.15248 -0.294
## studentLocKY 41.47222 34.59348 1.199
## studentLocLA 58.08130 40.16076 1.446
## studentLocMA 19.69160 33.08177 0.595
## studentLocMD 32.45002 32.82926 0.988
## studentLocME 35.37004 37.86356 0.934
## studentLocMI 47.79005 33.66638 1.420
## studentLocMN 65.00878 35.94366 1.809
## studentLocMO 14.20808 35.93350 0.395
## studentLocMS 36.18139 40.14259 0.901
## studentLocMT 172.35225 46.35961 3.718
## studentLocNC 38.97249 33.17042 1.175
## studentLocND -6.26191 46.37529 -0.135
## studentLocNE -2.70922 46.69107 -0.058
## studentLocNH 25.54774 34.58451 0.739
## studentLocNJ 29.42506 32.84324 0.896
## studentLocNM 0.98568 46.35581 0.021
## studentLocNV 55.62309 36.70257 1.516
## studentLocNY 28.97907 32.86567 0.882
## studentLocOH 35.85442 32.86269 1.091
## studentLocOK 18.14714 35.93632 0.505
## studentLocON 148.76452 36.67374 4.056
## studentLocOR 67.26994 37.86859 1.776
## studentLocPA 39.56166 32.82573 1.205
## studentLocPR 89.18911 46.34846 1.924
## studentLocRI 19.46314 35.06197 0.555
## studentLocSC 38.19504 33.58086 1.137
## studentLocSD 17.22388 46.38549 0.371
## studentLocTN 51.85806 33.61877 1.543
## studentLocTX 59.37620 33.13484 1.792
## studentLocUT 65.12679 46.35594 1.405
## studentLocVA 27.29474 32.83223 0.831
## studentLocVT 32.36576 34.79549 0.930
## studentLocWA 14.69486 34.81155 0.422
## studentLocWI 36.98325 34.04898 1.086
## studentLocWV 24.09984 32.80411 0.735
## stateIndicatorIn-State NA NA NA
## proxStudentTypeLong Commute -0.21729 2.27596 -0.095
## proxStudentTypeShort Commute 5.43824 1.08601 5.008
## scaledAcademAchiev 0.90378 0.03401 26.575
## affinityStatusNo Affinity 3.03372 0.72444 4.188
## expectedFamContrib 0.06969 0.01611 4.325
## Pr(>|t|)
## (Intercept) 0.026778 *
## studentGenderM 0.917185
## studentEthnBlack 1.85e-08 ***
## studentEthnHispanic 0.944931
## studentEthnAsian 0.861060
## studentEthnNative 0.268695
## studentEthnUnknown 1.26e-08 ***
## degreeFAssociate of Arts 0.162666
## degreeFBachelor Electronic Engr 0.921565
## degreeFBachelor Engr Tech 0.015463 *
## degreeFBachelor of Arts 0.018243 *
## degreeFBachelor of Fine Arts 0.402769
## degreeFBachelor of Multidisc. Studies 0.274517
## degreeFBachelor of Music 3.22e-09 ***
## degreeFBachelor of Science 0.003428 **
## degreeFBachelor of Science in Nursing 0.137088
## degreeFBachelor of Social Work 0.751564
## degreeFBS in Aerospace Engineering 0.077474 .
## degreeFBS in Agriculture 0.652839
## degreeFBS in Biometric Systems 0.322745
## degreeFBS in Business Administration 0.039167 *
## degreeFBS in Chemical Engineering 0.029349 *
## degreeFBS in Civil Engineering 2.21e-05 ***
## degreeFBS in Computer Engineering 0.081093 .
## degreeFBS in Computer Science 5.07e-06 ***
## degreeFBS in Electrical Engineering 0.007138 **
## degreeFBS in Forestry 0.474348
## degreeFBS in Industrial Engineering 0.093817 .
## degreeFBS in Journalism 0.038024 *
## degreeFBS in Landscape Architecture 0.010467 *
## degreeFBS in Mechanical Engineering 4.05e-05 ***
## degreeFBS in Mining Engineering 0.727042
## degreeFBS in Petroleum & Natl Gas Eng 0.056591 .
## degreeFBS in Physical Education 1.36e-05 ***
## degreeFBS in Recreation 0.233201
## degreeFDegree Not Declared 0.100428
## degreeFRegents Bachelor of Arts 0.713138
## degreeTypeRegent Degree NA
## degreeTypeDegree Not Declared NA
## degreeTypeAssociate Arts NA
## degreeTypeAssociate Applied Sci NA
## studentLocAK 0.880483
## studentLocAL 0.595166
## studentLocAP 0.505748
## studentLocAR 0.738903
## studentLocAZ 0.968962
## studentLocBC 0.025897 *
## studentLocCA 0.247984
## studentLocCO 0.162946
## studentLocCT 0.532038
## studentLocDC 0.507136
## studentLocDE 0.489961
## studentLocFL 0.181543
## studentLocFR 0.007654 **
## studentLocGA 0.084524 .
## studentLocIA 0.848057
## studentLocIL 0.230220
## studentLocIN 0.040423 *
## studentLocKS 0.768918
## studentLocKY 0.230622
## studentLocLA 0.148152
## studentLocMA 0.551699
## studentLocMD 0.322961
## studentLocME 0.350256
## studentLocMI 0.155785
## studentLocMN 0.070544 .
## studentLocMO 0.692558
## studentLocMS 0.367443
## studentLocMT 0.000202 ***
## studentLocNC 0.240061
## studentLocND 0.892594
## studentLocNE 0.953731
## studentLocNH 0.460107
## studentLocNJ 0.370319
## studentLocNM 0.983036
## studentLocNV 0.129681
## studentLocNY 0.377941
## studentLocOH 0.275287
## studentLocOK 0.613586
## studentLocON 5.03e-05 ***
## studentLocOR 0.075702 .
## studentLocPA 0.228159
## studentLocPR 0.054348 .
## studentLocRI 0.578836
## studentLocSC 0.255401
## studentLocSD 0.710408
## studentLocTN 0.122981
## studentLocTX 0.073175 .
## studentLocUT 0.160079
## studentLocVA 0.405805
## studentLocVT 0.352309
## studentLocWA 0.672944
## studentLocWI 0.277431
## studentLocWV 0.462567
## stateIndicatorIn-State NA
## proxStudentTypeLong Commute 0.923942
## proxStudentTypeShort Commute 5.62e-07 ***
## scaledAcademAchiev < 2e-16 ***
## affinityStatusNo Affinity 2.85e-05 ***
## expectedFamContrib 1.54e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 32.72 on 8495 degrees of freedom
## Multiple R-squared: 0.168, Adjusted R-squared: 0.1588
## F-statistic: 18.25 on 94 and 8495 DF, p-value: < 2.2e-16ncvTest(totalAwardWVUMod3)## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 493.3887 Df = 1 p = 2.608982e-109plot(totalAwardWVUMod3)## Warning: not plotting observations with leverage one:
## 480, 2813, 7441
## Warning: not plotting observations with leverage one:
## 480, 2813, 7441
## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produced## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produced
mmp(totalAwardWVUMod3)
par(mfrow = c(1, 2))
plot(log(totalAwardWVU) ~ modWVUAid$fitted.values)
plot(log(totalAwardWVU) ~ totalAwardWVUMod3$fitted.values)
par(mfrow = c(1, 2))
mmp(modWVUAid, sd = TRUE)
mmp(totalAwardWVUMod3, sd = TRUE)
#test model predictions
names(finDataTableWVU)## [1] "rule49Grant" "instEmployAid"
## [3] "instGrantAcademic" "instGrantAthletic"
## [5] "instGrantOther" "studentGender"
## [7] "studentEthn" "degreeF"
## [9] "degreeType" "studentLoc"
## [11] "stateIndicator" "proxStudentType"
## [13] "highSchoolGPA" "prevColGPA"
## [15] "highestACT" "totalSAT"
## [17] "scoreGED" "scaledAcademAchiev"
## [19] "affinityStatus" "expectedFamContrib"
## [21] "totalAwardWVU" "totalAwardnonWVU"
## [23] "totalAwardPromScholar" "aidStudentWVU"
## [25] "aidStudentnonWVU" "aidStudentPromScholar"
## [27] "highSchoolGPA.NA" "prevColGPA.NA"
## [29] "highestACT.NA" "totalSAT.NA"
## [31] "scoreGED.NA" "expectedFamContrib.NA"
## [33] "studentEthn.NA" "scaledAcademAchiev.NA"which(finDataTableWVU[,21] > 40000)## [1] 1355 3654 7276 7369 7442fitResults <- predict(modWVUAid, newdata = finDataTableWVU[1355,], type = "response")
(fitResults)^2## 1355
## 3551.281finDataTableWVU[1355, 21]## [1] 41170#Unfortunately while the models fit that data well, testing it with the predictions about show that the results do not seem to accurately predict totalAwardWVUModeling students who received no WVU direct aid with those who did receive WVU aid created mixed results and lowered the quality of the prediction. By modelling them separately, we can provide better insight to the university.
By modeling just the population that did receive at least some totalAwardWVU we will get more accurate predicitors. With this, we can see what variables were important for increasing the amount of WVU aid that the university decided to issue to a student.
#run model on subset of students that received WVU aid #AL12 Total WVU Award > 0
finDataTableWVU_AL12 <- subset(finDataTableWVU, totalAwardWVU > 0)
dim(finDataTableWVU_AL12) ## [1] 4396 34summary(finDataTableWVU_AL12)## rule49Grant instEmployAid instGrantAcademic instGrantAthletic
## Min. : 0 Min. : 0.0 Min. : 0 Min. : 0.0
## 1st Qu.: 0 1st Qu.: 0.0 1st Qu.: 0 1st Qu.: 0.0
## Median : 0 Median : 0.0 Median : 0 Median : 0.0
## Mean : 1856 Mean : 369.9 Mean : 1029 Mean : 588.6
## 3rd Qu.: 3000 3rd Qu.: 0.0 3rd Qu.: 2000 3rd Qu.: 0.0
## Max. :21336 Max. :17233.0 Max. :15603 Max. :41170.0
##
## instGrantOther studentGender studentEthn
## Min. : 0 F:2068 White :1638
## 1st Qu.: 0 M:2328 Black : 169
## Median : 0 Hispanic: 31
## Mean : 367 Asian : 51
## 3rd Qu.: 0 Native : 8
## Max. :9338 Unknown :2499
##
## degreeF degreeType
## Bachelor of Science :1925 Bachelor Degree :4018
## Bachelor of Arts : 990 Regent Degree : 1
## BS in Business Administration : 396 Degree Not Declared : 50
## Associate of Arts : 302 Associate Arts : 302
## BS in Journalism : 126 Associate Applied Sci: 25
## Bachelor of Multidisc. Studies: 76
## (Other) : 581
## studentLoc stateIndicator proxStudentType
## WV :2324 Out-of-State:2072 Res or Out-of-State:3444
## PA : 540 In-State :2324 Long Commute : 124
## MD : 376 Short Commute : 828
## VA : 296
## NJ : 201
## OH : 188
## (Other): 471
## highSchoolGPA prevColGPA highestACT totalSAT
## Min. : 1.00 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.: 68.39 1st Qu.: 1.00 1st Qu.: 37.33 1st Qu.: 39.08
## Median : 78.21 Median : 72.03 Median : 53.68 Median : 52.62
## Mean : 75.92 Mean : 52.50 Mean : 46.62 Mean : 46.11
## 3rd Qu.: 88.90 3rd Qu.: 90.59 3rd Qu.: 64.58 3rd Qu.: 61.08
## Max. :100.00 Max. :100.00 Max. :100.00 Max. :100.00
##
## scoreGED scaledAcademAchiev affinityStatus
## Min. : 1.000 Min. : 23.03 Some Affinity:1939
## 1st Qu.: 1.000 1st Qu.: 62.23 No Affinity :2457
## Median : 1.000 Median : 68.98
## Mean : 2.145 Mean : 68.35
## 3rd Qu.: 1.000 3rd Qu.: 75.07
## Max. :100.000 Max. :100.00
##
## expectedFamContrib totalAwardWVU totalAwardnonWVU totalAwardPromScholar
## Min. : 0.000 Min. : 25 Min. : 0 Min. : 0
## 1st Qu.: 2.024 1st Qu.: 1500 1st Qu.: 2375 1st Qu.: 0
## Median : 11.176 Median : 3000 Median : 6339 Median : 0
## Mean : 19.440 Mean : 4211 Mean : 8397 Mean :1558
## 3rd Qu.: 27.540 3rd Qu.: 5000 3rd Qu.:13054 3rd Qu.:4750
## Max. :100.000 Max. :43560 Max. :42328 Max. :7125
##
## aidStudentWVU aidStudentnonWVU
## Did not received WVU aid: 0 Did not received other aid: 942
## Received WVU aid :4396 Received other aid :3454
##
##
##
##
##
## aidStudentPromScholar highSchoolGPA.NA prevColGPA.NA highestACT.NA
## Is not Promise:2899 Mode :logical Mode :logical Mode :logical
## Is Promise :1497 FALSE:4315 FALSE:2733 FALSE:3502
## TRUE :81 TRUE :1663 TRUE :894
## NA's :0 NA's :0 NA's :0
##
##
##
## totalSAT.NA scoreGED.NA expectedFamContrib.NA studentEthn.NA
## Mode :logical Mode :logical Mode :logical Mode :logical
## FALSE:3610 FALSE:65 FALSE:4260 FALSE:4377
## TRUE :786 TRUE :4331 TRUE :136 TRUE :19
## NA's :0 NA's :0 NA's :0 NA's :0
##
##
##
## scaledAcademAchiev.NA
## Mode :logical
## FALSE:4396
## NA's :0
##
##
##
## sum(finDataTableWVU_AL12$totalAwardWVU)## [1] 18510879modWVUAid_1 <- lm(totalAwardWVU ~ studentGender + studentEthn + degreeF + studentLoc + proxStudentType + affinityStatus + expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU + aidStudentPromScholar + highestACT + highestACT.NA + totalSAT + totalSAT.NA + totalAwardnonWVU + totalAwardPromScholar + highSchoolGPA + highSchoolGPA.NA + prevColGPA + prevColGPA.NA + scoreGED + scoreGED.NA + scaledAcademAchiev, data = finDataTableWVU_AL12)
summary(modWVUAid_1)##
## Call:
## lm(formula = totalAwardWVU ~ studentGender + studentEthn + degreeF +
## studentLoc + proxStudentType + affinityStatus + expectedFamContrib +
## expectedFamContrib.NA + aidStudentnonWVU + aidStudentPromScholar +
## highestACT + highestACT.NA + totalSAT + totalSAT.NA + totalAwardnonWVU +
## totalAwardPromScholar + highSchoolGPA + highSchoolGPA.NA +
## prevColGPA + prevColGPA.NA + scoreGED + scoreGED.NA + scaledAcademAchiev,
## data = finDataTableWVU_AL12)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13043 -2157 -716 906 37444
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 8.457e+02 5.328e+03 0.159
## studentGenderM 5.309e+01 1.429e+02 0.371
## studentEthnBlack 3.457e+03 3.760e+02 9.195
## studentEthnHispanic 1.061e+03 8.085e+02 1.312
## studentEthnAsian 8.626e+01 6.403e+02 0.135
## studentEthnNative 3.054e+03 1.579e+03 1.934
## studentEthnUnknown 6.965e+01 1.487e+02 0.468
## degreeFAssociate of Arts 2.553e+02 9.298e+02 0.275
## degreeFBachelor Engr Tech 5.240e+03 2.719e+03 1.927
## degreeFBachelor of Arts 2.181e+03 9.150e+02 2.383
## degreeFBachelor of Fine Arts 1.383e+03 1.083e+03 1.277
## degreeFBachelor of Multidisc. Studies 1.336e+03 1.037e+03 1.289
## degreeFBachelor of Music 3.241e+03 1.067e+03 3.037
## degreeFBachelor of Science 1.881e+03 9.096e+02 2.068
## degreeFBachelor of Science in Nursing 1.345e+03 1.906e+03 0.706
## degreeFBachelor of Social Work 1.488e+03 1.418e+03 1.050
## degreeFBS in Aerospace Engineering 3.713e+03 1.225e+03 3.031
## degreeFBS in Agriculture 1.063e+03 1.233e+03 0.862
## degreeFBS in Biometric Systems 2.582e+03 2.182e+03 1.183
## degreeFBS in Business Administration 1.687e+03 9.342e+02 1.806
## degreeFBS in Chemical Engineering 3.576e+03 1.236e+03 2.893
## degreeFBS in Civil Engineering 2.525e+03 1.167e+03 2.164
## degreeFBS in Computer Engineering 1.386e+03 1.363e+03 1.016
## degreeFBS in Computer Science 2.955e+03 1.122e+03 2.635
## degreeFBS in Electrical Engineering 2.525e+03 1.243e+03 2.031
## degreeFBS in Forestry 1.041e+03 1.503e+03 0.693
## degreeFBS in Industrial Engineering 4.614e+03 1.404e+03 3.286
## degreeFBS in Journalism 1.982e+03 9.888e+02 2.004
## degreeFBS in Landscape Architecture 1.217e+03 1.414e+03 0.861
## degreeFBS in Mechanical Engineering 3.953e+03 1.146e+03 3.451
## degreeFBS in Mining Engineering -1.187e+03 1.908e+03 -0.622
## degreeFBS in Petroleum & Natl Gas Eng 1.987e+03 1.242e+03 1.600
## degreeFBS in Physical Education 2.200e+03 1.546e+03 1.423
## degreeFBS in Recreation -9.176e+02 2.396e+03 -0.383
## degreeFDegree Not Declared 2.090e+02 1.096e+03 0.191
## degreeFRegents Bachelor of Arts 6.978e+02 4.532e+03 0.154
## studentLocAR -3.129e+03 5.206e+03 -0.601
## studentLocBC 2.692e+04 5.165e+03 5.213
## studentLocCA 3.010e+03 2.783e+03 1.082
## studentLocCO 6.270e+03 3.283e+03 1.910
## studentLocCT -1.355e+03 2.764e+03 -0.490
## studentLocDC -5.956e+02 2.883e+03 -0.207
## studentLocDE 1.715e+03 2.818e+03 0.609
## studentLocFL 1.648e+03 2.711e+03 0.608
## studentLocFR 3.519e+03 2.803e+03 1.256
## studentLocGA 6.620e+03 2.770e+03 2.390
## studentLocIL 3.037e+03 2.818e+03 1.078
## studentLocIN 1.092e+04 3.050e+03 3.579
## studentLocKY -1.718e+02 3.115e+03 -0.055
## studentLocLA 7.526e+03 5.147e+03 1.462
## studentLocMA 1.466e+02 2.807e+03 0.052
## studentLocMD 3.968e+01 2.624e+03 0.015
## studentLocME -9.087e+02 4.081e+03 -0.223
## studentLocMI 7.377e+03 2.969e+03 2.485
## studentLocMN 9.862e+03 3.669e+03 2.688
## studentLocMO 1.519e+03 5.147e+03 0.295
## studentLocMS 1.829e+03 5.145e+03 0.355
## studentLocMT 2.929e+04 5.159e+03 5.677
## studentLocNC 2.934e+03 2.789e+03 1.052
## studentLocNH -1.856e+03 3.295e+03 -0.563
## studentLocNJ 3.416e+02 2.634e+03 0.130
## studentLocNV 2.165e+03 3.661e+03 0.591
## studentLocNY 4.657e+02 2.646e+03 0.176
## studentLocOH 3.851e+02 2.633e+03 0.146
## studentLocOK 1.356e+04 5.147e+03 2.635
## studentLocON 1.754e+04 3.436e+03 5.104
## studentLocOR 1.040e+04 4.079e+03 2.550
## studentLocPA 1.139e+03 2.621e+03 0.435
## studentLocPR 6.632e+03 5.151e+03 1.287
## studentLocRI -3.113e+02 4.078e+03 -0.076
## studentLocSC 2.533e+03 2.939e+03 0.862
## studentLocSD -1.730e+03 5.157e+03 -0.335
## studentLocTN 1.480e+03 2.855e+03 0.518
## studentLocTX 6.634e+03 2.735e+03 2.425
## studentLocUT -3.846e+02 5.150e+03 -0.075
## studentLocVA -2.046e+02 2.625e+03 -0.078
## studentLocVT -1.824e+03 3.446e+03 -0.529
## studentLocWA 1.042e+03 4.101e+03 0.254
## studentLocWI 2.169e+03 3.109e+03 0.697
## studentLocWV -4.469e+01 2.622e+03 -0.017
## proxStudentTypeLong Commute -9.106e+01 4.178e+02 -0.218
## proxStudentTypeShort Commute 1.446e+03 2.082e+02 6.947
## affinityStatusNo Affinity 3.421e+02 1.399e+02 2.446
## expectedFamContrib -1.183e+01 3.073e+00 -3.848
## expectedFamContrib.NATRUE 9.537e+02 4.199e+02 2.271
## aidStudentnonWVUReceived other aid -1.373e+02 2.327e+02 -0.590
## aidStudentPromScholarIs Promise -2.816e+03 9.439e+02 -2.983
## highestACT 5.279e+01 1.019e+01 5.179
## highestACT.NATRUE 3.419e+03 6.819e+02 5.014
## totalSAT 7.686e+01 1.090e+01 7.054
## totalSAT.NATRUE 4.122e+03 7.381e+02 5.585
## totalAwardnonWVU -5.041e-02 1.174e-02 -4.294
## totalAwardPromScholar 1.826e-01 2.019e-01 0.904
## highSchoolGPA 2.402e+01 1.095e+01 2.194
## highSchoolGPA.NATRUE 2.362e+03 9.431e+02 2.505
## prevColGPA 2.515e+00 9.760e+00 0.258
## prevColGPA.NATRUE 1.100e+02 7.079e+02 0.155
## scoreGED -6.345e+01 5.564e+01 -1.140
## scoreGED.NATRUE -4.897e+03 4.338e+03 -1.129
## scaledAcademAchiev -3.922e+01 2.839e+01 -1.382
## Pr(>|t|)
## (Intercept) 0.873880
## studentGenderM 0.710380
## studentEthnBlack < 2e-16 ***
## studentEthnHispanic 0.189527
## studentEthnAsian 0.892840
## studentEthnNative 0.053234 .
## studentEthnUnknown 0.639565
## degreeFAssociate of Arts 0.783629
## degreeFBachelor Engr Tech 0.054057 .
## degreeFBachelor of Arts 0.017212 *
## degreeFBachelor of Fine Arts 0.201557
## degreeFBachelor of Multidisc. Studies 0.197457
## degreeFBachelor of Music 0.002403 **
## degreeFBachelor of Science 0.038723 *
## degreeFBachelor of Science in Nursing 0.480370
## degreeFBachelor of Social Work 0.293987
## degreeFBS in Aerospace Engineering 0.002452 **
## degreeFBS in Agriculture 0.388724
## degreeFBS in Biometric Systems 0.236815
## degreeFBS in Business Administration 0.070972 .
## degreeFBS in Chemical Engineering 0.003841 **
## degreeFBS in Civil Engineering 0.030539 *
## degreeFBS in Computer Engineering 0.309454
## degreeFBS in Computer Science 0.008456 **
## degreeFBS in Electrical Engineering 0.042286 *
## degreeFBS in Forestry 0.488360
## degreeFBS in Industrial Engineering 0.001023 **
## degreeFBS in Journalism 0.045101 *
## degreeFBS in Landscape Architecture 0.389538
## degreeFBS in Mechanical Engineering 0.000564 ***
## degreeFBS in Mining Engineering 0.533723
## degreeFBS in Petroleum & Natl Gas Eng 0.109590
## degreeFBS in Physical Education 0.154758
## degreeFBS in Recreation 0.701810
## degreeFDegree Not Declared 0.848708
## degreeFRegents Bachelor of Arts 0.877628
## studentLocAR 0.547865
## studentLocBC 1.95e-07 ***
## studentLocCA 0.279413
## studentLocCO 0.056208 .
## studentLocCT 0.623903
## studentLocDC 0.836321
## studentLocDE 0.542734
## studentLocFL 0.543322
## studentLocFR 0.209349
## studentLocGA 0.016884 *
## studentLocIL 0.281247
## studentLocIN 0.000349 ***
## studentLocKY 0.956025
## studentLocLA 0.143738
## studentLocMA 0.958351
## studentLocMD 0.987936
## studentLocME 0.823830
## studentLocMI 0.012994 *
## studentLocMN 0.007208 **
## studentLocMO 0.767905
## studentLocMS 0.722316
## studentLocMT 1.46e-08 ***
## studentLocNC 0.292949
## studentLocNH 0.573302
## studentLocNJ 0.896796
## studentLocNV 0.554319
## studentLocNY 0.860296
## studentLocOH 0.883718
## studentLocOK 0.008433 **
## studentLocON 3.47e-07 ***
## studentLocOR 0.010806 *
## studentLocPA 0.663941
## studentLocPR 0.198036
## studentLocRI 0.939161
## studentLocSC 0.388881
## studentLocSD 0.737322
## studentLocTN 0.604181
## studentLocTX 0.015334 *
## studentLocUT 0.940479
## studentLocVA 0.937881
## studentLocVT 0.596614
## studentLocWA 0.799372
## studentLocWI 0.485545
## studentLocWV 0.986399
## proxStudentTypeLong Commute 0.827477
## proxStudentTypeShort Commute 4.29e-12 ***
## affinityStatusNo Affinity 0.014497 *
## expectedFamContrib 0.000121 ***
## expectedFamContrib.NATRUE 0.023187 *
## aidStudentnonWVUReceived other aid 0.555352
## aidStudentPromScholarIs Promise 0.002867 **
## highestACT 2.33e-07 ***
## highestACT.NATRUE 5.55e-07 ***
## totalSAT 2.02e-12 ***
## totalSAT.NATRUE 2.48e-08 ***
## totalAwardnonWVU 1.80e-05 ***
## totalAwardPromScholar 0.365910
## highSchoolGPA 0.028289 *
## highSchoolGPA.NATRUE 0.012282 *
## prevColGPA 0.796662
## prevColGPA.NATRUE 0.876545
## scoreGED 0.254208
## scoreGED.NATRUE 0.258976
## scaledAcademAchiev 0.167185
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4423 on 4296 degrees of freedom
## Multiple R-squared: 0.2351, Adjusted R-squared: 0.2174
## F-statistic: 13.33 on 99 and 4296 DF, p-value: < 2.2e-16anova(modWVUAid_1) #promScholar aid, prevColGPA, scoreGED, and scaledAcademAchiev amount is not sig## Analysis of Variance Table
##
## Response: totalAwardWVU
## Df Sum Sq Mean Sq F value Pr(>F)
## studentGender 1 1.5281e+08 152813204 7.8113 0.005215 **
## studentEthn 5 1.8847e+09 376934139 19.2676 < 2.2e-16 ***
## degreeF 29 3.4059e+09 117446285 6.0035 < 2.2e-16 ***
## studentLoc 44 1.1679e+10 265438147 13.5683 < 2.2e-16 ***
## proxStudentType 2 2.2013e+09 1100647812 56.2614 < 2.2e-16 ***
## affinityStatus 1 1.3637e+08 136367153 6.9706 0.008316 **
## expectedFamContrib 1 1.5669e+08 156692734 8.0096 0.004675 **
## expectedFamContrib.NA 1 4.2053e+08 420530903 21.4961 3.651e-06 ***
## aidStudentnonWVU 1 6.7344e+08 673441362 34.4241 4.766e-09 ***
## aidStudentPromScholar 1 7.2936e+08 729362741 37.2826 1.112e-09 ***
## highestACT 1 7.6638e+07 76638455 3.9175 0.047850 *
## highestACT.NA 1 1.4968e+09 1496841056 76.5135 < 2.2e-16 ***
## totalSAT 1 7.0771e+08 707708990 36.1757 1.953e-09 ***
## totalSAT.NA 1 1.4898e+09 1489793942 76.1533 < 2.2e-16 ***
## totalAwardnonWVU 1 3.7087e+08 370869041 18.9576 1.368e-05 ***
## totalAwardPromScholar 1 1.5235e+07 15234940 0.7788 0.377570
## highSchoolGPA 1 1.4633e+07 14633374 0.7480 0.387156
## highSchoolGPA.NA 1 8.9334e+07 89334167 4.5665 0.032660 *
## prevColGPA 1 2.3815e+07 23815079 1.2173 0.269944
## prevColGPA.NA 1 2.6160e+07 26160439 1.3372 0.247587
## scoreGED 1 2.2754e+06 2275429 0.1163 0.733086
## scoreGED.NA 1 3.3375e+07 33375106 1.7060 0.191572
## scaledAcademAchiev 1 3.7339e+07 37339193 1.9087 0.167185
## Residuals 4296 8.4043e+10 19563091
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1modWVUAid_2 <- lm(totalAwardWVU ~ studentGender + studentEthn + degreeF + studentLoc + proxStudentType + affinityStatus + expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU + aidStudentPromScholar + highSchoolGPA + highSchoolGPA.NA + highestACT + highestACT.NA + totalSAT + totalSAT.NA + totalAwardnonWVU, data = finDataTableWVU_AL12)
summary(modWVUAid_2) ##
## Call:
## lm(formula = totalAwardWVU ~ studentGender + studentEthn + degreeF +
## studentLoc + proxStudentType + affinityStatus + expectedFamContrib +
## expectedFamContrib.NA + aidStudentnonWVU + aidStudentPromScholar +
## highSchoolGPA + highSchoolGPA.NA + highestACT + highestACT.NA +
## totalSAT + totalSAT.NA + totalAwardnonWVU, data = finDataTableWVU_AL12)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13066 -2169 -705 890 37463
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) -4.268e+03 2.834e+03 -1.506
## studentGenderM 6.219e+01 1.428e+02 0.435
## studentEthnBlack 3.470e+03 3.756e+02 9.240
## studentEthnHispanic 1.028e+03 8.080e+02 1.272
## studentEthnAsian 1.391e+02 6.391e+02 0.218
## studentEthnNative 3.005e+03 1.579e+03 1.904
## studentEthnUnknown 7.480e+01 1.486e+02 0.503
## degreeFAssociate of Arts 2.418e+02 9.268e+02 0.261
## degreeFBachelor Engr Tech 5.151e+03 2.719e+03 1.895
## degreeFBachelor of Arts 2.215e+03 9.140e+02 2.424
## degreeFBachelor of Fine Arts 1.441e+03 1.082e+03 1.332
## degreeFBachelor of Multidisc. Studies 1.349e+03 1.036e+03 1.302
## degreeFBachelor of Music 3.224e+03 1.067e+03 3.022
## degreeFBachelor of Science 1.901e+03 9.088e+02 2.092
## degreeFBachelor of Science in Nursing 1.342e+03 1.903e+03 0.705
## degreeFBachelor of Social Work 1.496e+03 1.416e+03 1.056
## degreeFBS in Aerospace Engineering 3.730e+03 1.223e+03 3.049
## degreeFBS in Agriculture 1.076e+03 1.232e+03 0.873
## degreeFBS in Biometric Systems 2.710e+03 2.181e+03 1.242
## degreeFBS in Business Administration 1.709e+03 9.334e+02 1.831
## degreeFBS in Chemical Engineering 3.493e+03 1.235e+03 2.828
## degreeFBS in Civil Engineering 2.630e+03 1.165e+03 2.257
## degreeFBS in Computer Engineering 1.417e+03 1.361e+03 1.041
## degreeFBS in Computer Science 2.989e+03 1.120e+03 2.668
## degreeFBS in Electrical Engineering 2.587e+03 1.242e+03 2.083
## degreeFBS in Forestry 1.064e+03 1.502e+03 0.709
## degreeFBS in Industrial Engineering 4.644e+03 1.403e+03 3.310
## degreeFBS in Journalism 2.008e+03 9.880e+02 2.032
## degreeFBS in Landscape Architecture 1.307e+03 1.413e+03 0.925
## degreeFBS in Mechanical Engineering 3.949e+03 1.145e+03 3.450
## degreeFBS in Mining Engineering -1.099e+03 1.907e+03 -0.576
## degreeFBS in Petroleum & Natl Gas Eng 1.960e+03 1.240e+03 1.580
## degreeFBS in Physical Education 2.243e+03 1.546e+03 1.451
## degreeFBS in Recreation -9.628e+02 2.396e+03 -0.402
## degreeFDegree Not Declared 3.068e+02 1.094e+03 0.280
## degreeFRegents Bachelor of Arts 4.693e+02 4.527e+03 0.104
## studentLocAR -3.088e+03 5.206e+03 -0.593
## studentLocBC 2.726e+04 5.161e+03 5.282
## studentLocCA 3.076e+03 2.782e+03 1.106
## studentLocCO 6.352e+03 3.282e+03 1.936
## studentLocCT -1.234e+03 2.762e+03 -0.447
## studentLocDC -5.164e+02 2.883e+03 -0.179
## studentLocDE 1.789e+03 2.816e+03 0.635
## studentLocFL 1.723e+03 2.710e+03 0.636
## studentLocFR 3.600e+03 2.802e+03 1.285
## studentLocGA 6.728e+03 2.768e+03 2.431
## studentLocIL 3.142e+03 2.817e+03 1.115
## studentLocIN 1.097e+04 3.050e+03 3.597
## studentLocKY 2.400e+00 3.114e+03 0.001
## studentLocLA 7.690e+03 5.145e+03 1.495
## studentLocMA 1.840e+02 2.806e+03 0.066
## studentLocMD 1.111e+02 2.623e+03 0.042
## studentLocME -7.309e+02 4.080e+03 -0.179
## studentLocMI 7.481e+03 2.967e+03 2.521
## studentLocMN 9.892e+03 3.667e+03 2.698
## studentLocMO 1.709e+03 5.146e+03 0.332
## studentLocMS 1.875e+03 5.146e+03 0.364
## studentLocMT 2.921e+04 5.160e+03 5.662
## studentLocNC 3.024e+03 2.788e+03 1.085
## studentLocNH -1.978e+03 3.288e+03 -0.602
## studentLocNJ 4.170e+02 2.633e+03 0.158
## studentLocNV 2.138e+03 3.662e+03 0.584
## studentLocNY 5.366e+02 2.645e+03 0.203
## studentLocOH 4.617e+02 2.632e+03 0.175
## studentLocOK 1.366e+04 5.147e+03 2.654
## studentLocON 1.766e+04 3.434e+03 5.142
## studentLocOR 1.042e+04 4.080e+03 2.553
## studentLocPA 1.198e+03 2.620e+03 0.457
## studentLocPR 6.634e+03 5.152e+03 1.288
## studentLocRI -2.387e+02 4.078e+03 -0.059
## studentLocSC 2.603e+03 2.938e+03 0.886
## studentLocSD -1.604e+03 5.158e+03 -0.311
## studentLocTN 1.464e+03 2.854e+03 0.513
## studentLocTX 6.700e+03 2.735e+03 2.450
## studentLocUT -2.490e+02 5.149e+03 -0.048
## studentLocVA -1.078e+02 2.624e+03 -0.041
## studentLocVT -1.725e+03 3.444e+03 -0.501
## studentLocWA 1.165e+03 4.098e+03 0.284
## studentLocWI 2.340e+03 3.107e+03 0.753
## studentLocWV 1.632e+01 2.621e+03 0.006
## proxStudentTypeLong Commute -6.839e+01 4.176e+02 -0.164
## proxStudentTypeShort Commute 1.454e+03 2.077e+02 7.003
## affinityStatusNo Affinity 3.780e+02 1.385e+02 2.730
## expectedFamContrib -1.166e+01 3.067e+00 -3.802
## expectedFamContrib.NATRUE 9.405e+02 4.193e+02 2.243
## aidStudentnonWVUReceived other aid -1.342e+02 2.327e+02 -0.577
## aidStudentPromScholarIs Promise -1.979e+03 2.220e+02 -8.916
## highSchoolGPA 1.037e+01 5.230e+00 1.982
## highSchoolGPA.NATRUE 1.383e+03 6.565e+02 2.107
## highestACT 4.080e+01 6.045e+00 6.749
## highestACT.NATRUE 2.604e+03 3.804e+02 6.844
## totalSAT 6.486e+01 6.527e+00 9.937
## totalSAT.NATRUE 3.268e+03 4.011e+02 8.149
## totalAwardnonWVU -4.975e-02 1.171e-02 -4.250
## Pr(>|t|)
## (Intercept) 0.132185
## studentGenderM 0.663235
## studentEthnBlack < 2e-16 ***
## studentEthnHispanic 0.203528
## studentEthnAsian 0.827756
## studentEthnNative 0.057005 .
## studentEthnUnknown 0.614654
## degreeFAssociate of Arts 0.794198
## degreeFBachelor Engr Tech 0.058203 .
## degreeFBachelor of Arts 0.015408 *
## degreeFBachelor of Fine Arts 0.182852
## degreeFBachelor of Multidisc. Studies 0.192827
## degreeFBachelor of Music 0.002524 **
## degreeFBachelor of Science 0.036484 *
## degreeFBachelor of Science in Nursing 0.480829
## degreeFBachelor of Social Work 0.290813
## degreeFBS in Aerospace Engineering 0.002310 **
## degreeFBS in Agriculture 0.382637
## degreeFBS in Biometric Systems 0.214133
## degreeFBS in Business Administration 0.067219 .
## degreeFBS in Chemical Engineering 0.004702 **
## degreeFBS in Civil Engineering 0.024063 *
## degreeFBS in Computer Engineering 0.298151
## degreeFBS in Computer Science 0.007652 **
## degreeFBS in Electrical Engineering 0.037301 *
## degreeFBS in Forestry 0.478482
## degreeFBS in Industrial Engineering 0.000942 ***
## degreeFBS in Journalism 0.042218 *
## degreeFBS in Landscape Architecture 0.354868
## degreeFBS in Mechanical Engineering 0.000567 ***
## degreeFBS in Mining Engineering 0.564393
## degreeFBS in Petroleum & Natl Gas Eng 0.114072
## degreeFBS in Physical Education 0.146757
## degreeFBS in Recreation 0.687764
## degreeFDegree Not Declared 0.779271
## degreeFRegents Bachelor of Arts 0.917437
## studentLocAR 0.553202
## studentLocBC 1.34e-07 ***
## studentLocCA 0.268947
## studentLocCO 0.052959 .
## studentLocCT 0.655089
## studentLocDC 0.857829
## studentLocDE 0.525397
## studentLocFL 0.524872
## studentLocFR 0.198860
## studentLocGA 0.015115 *
## studentLocIL 0.264789
## studentLocIN 0.000326 ***
## studentLocKY 0.999385
## studentLocLA 0.135076
## studentLocMA 0.947734
## studentLocMD 0.966210
## studentLocME 0.857847
## studentLocMI 0.011740 *
## studentLocMN 0.007009 **
## studentLocMO 0.739846
## studentLocMS 0.715524
## studentLocMT 1.60e-08 ***
## studentLocNC 0.278161
## studentLocNH 0.547529
## studentLocNJ 0.874150
## studentLocNV 0.559385
## studentLocNY 0.839249
## studentLocOH 0.860729
## studentLocOK 0.007981 **
## studentLocON 2.84e-07 ***
## studentLocOR 0.010701 *
## studentLocPA 0.647549
## studentLocPR 0.197937
## studentLocRI 0.953317
## studentLocSC 0.375710
## studentLocSD 0.755826
## studentLocTN 0.608118
## studentLocTX 0.014320 *
## studentLocUT 0.961434
## studentLocVA 0.967222
## studentLocVT 0.616567
## studentLocWA 0.776169
## studentLocWI 0.451488
## studentLocWV 0.995032
## proxStudentTypeLong Commute 0.869913
## proxStudentTypeShort Commute 2.90e-12 ***
## affinityStatusNo Affinity 0.006363 **
## expectedFamContrib 0.000145 ***
## expectedFamContrib.NATRUE 0.024960 *
## aidStudentnonWVUReceived other aid 0.563993
## aidStudentPromScholarIs Promise < 2e-16 ***
## highSchoolGPA 0.047517 *
## highSchoolGPA.NATRUE 0.035163 *
## highestACT 1.68e-11 ***
## highestACT.NATRUE 8.77e-12 ***
## totalSAT < 2e-16 ***
## totalSAT.NATRUE 4.77e-16 ***
## totalAwardnonWVU 2.18e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4424 on 4302 degrees of freedom
## Multiple R-squared: 0.2338, Adjusted R-squared: 0.2172
## F-statistic: 14.11 on 93 and 4302 DF, p-value: < 2.2e-16anova(modWVUAid_2)## Analysis of Variance Table
##
## Response: totalAwardWVU
## Df Sum Sq Mean Sq F value Pr(>F)
## studentGender 1 1.5281e+08 152813204 7.8092 0.005221 **
## studentEthn 5 1.8847e+09 376934139 19.2623 < 2.2e-16 ***
## degreeF 29 3.4059e+09 117446285 6.0018 < 2.2e-16 ***
## studentLoc 44 1.1679e+10 265438147 13.5646 < 2.2e-16 ***
## proxStudentType 2 2.2013e+09 1100647812 56.2460 < 2.2e-16 ***
## affinityStatus 1 1.3637e+08 136367153 6.9687 0.008325 **
## expectedFamContrib 1 1.5669e+08 156692734 8.0074 0.004680 **
## expectedFamContrib.NA 1 4.2053e+08 420530903 21.4902 3.662e-06 ***
## aidStudentnonWVU 1 6.7344e+08 673441362 34.4146 4.788e-09 ***
## aidStudentPromScholar 1 7.2936e+08 729362741 37.2723 1.118e-09 ***
## highSchoolGPA 1 8.5486e+07 85486305 4.3686 0.036666 *
## highSchoolGPA.NA 1 1.8821e+08 188212314 9.6181 0.001939 **
## highestACT 1 6.7332e+07 67332023 3.4408 0.063672 .
## highestACT.NA 1 1.4615e+09 1461545051 74.6888 < 2.2e-16 ***
## totalSAT 1 6.9566e+08 695656452 35.5499 2.685e-09 ***
## totalSAT.NA 1 1.3917e+09 1391718584 71.1204 < 2.2e-16 ***
## totalAwardnonWVU 1 3.5353e+08 353534991 18.0666 2.178e-05 ***
## Residuals 4302 8.4184e+10 19568473
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#model transformation require(MASS) bc <- boxcox(modWVUAid_2)
#The optimal transformation has a parameter close to 0 - use log
#find the approximate mle as the x-value that yields the maximum bc$x[bc$y==max(bc$y)]
modWVUAid_3 <- lm(log(totalAwardWVU) ~ studentGender + studentEthn + degreeF + studentLoc + proxStudentType + affinityStatus + expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU + aidStudentPromScholar + highestACT + highestACT.NA + totalSAT + totalSAT.NA + totalAwardnonWVU, data = finDataTableWVU_AL12)
summary(modWVUAid_3)##
## Call:
## lm(formula = log(totalAwardWVU) ~ studentGender + studentEthn +
## degreeF + studentLoc + proxStudentType + affinityStatus +
## expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU +
## aidStudentPromScholar + highestACT + highestACT.NA + totalSAT +
## totalSAT.NA + totalAwardnonWVU, data = finDataTableWVU_AL12)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.8253 -0.4349 0.0438 0.4598 2.9691
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 5.848e+00 5.285e-01 11.064
## studentGenderM 3.377e-02 2.671e-02 1.264
## studentEthnBlack 5.234e-01 7.040e-02 7.434
## studentEthnHispanic 3.127e-01 1.520e-01 2.057
## studentEthnAsian 4.465e-02 1.201e-01 0.372
## studentEthnNative 5.226e-01 2.970e-01 1.760
## studentEthnUnknown 2.545e-02 2.793e-02 0.911
## degreeFAssociate of Arts 2.050e-01 1.743e-01 1.176
## degreeFBachelor Engr Tech 1.553e+00 5.107e-01 3.042
## degreeFBachelor of Arts 6.537e-01 1.720e-01 3.802
## degreeFBachelor of Fine Arts 4.693e-01 2.035e-01 2.306
## degreeFBachelor of Multidisc. Studies 4.366e-01 1.948e-01 2.241
## degreeFBachelor of Music 1.000e+00 2.007e-01 4.985
## degreeFBachelor of Science 6.412e-01 1.710e-01 3.751
## degreeFBachelor of Science in Nursing 7.286e-01 3.573e-01 2.039
## degreeFBachelor of Social Work 3.920e-01 2.663e-01 1.472
## degreeFBS in Aerospace Engineering 9.210e-01 2.300e-01 4.004
## degreeFBS in Agriculture 4.291e-01 2.318e-01 1.851
## degreeFBS in Biometric Systems 1.014e+00 4.100e-01 2.472
## degreeFBS in Business Administration 5.981e-01 1.756e-01 3.406
## degreeFBS in Chemical Engineering 9.829e-01 2.322e-01 4.233
## degreeFBS in Civil Engineering 7.868e-01 2.192e-01 3.590
## degreeFBS in Computer Engineering 5.770e-01 2.561e-01 2.253
## degreeFBS in Computer Science 8.690e-01 2.107e-01 4.124
## degreeFBS in Electrical Engineering 8.836e-01 2.333e-01 3.787
## degreeFBS in Forestry 3.366e-01 2.825e-01 1.191
## degreeFBS in Industrial Engineering 1.038e+00 2.639e-01 3.933
## degreeFBS in Journalism 6.834e-01 1.859e-01 3.677
## degreeFBS in Landscape Architecture 6.679e-01 2.658e-01 2.512
## degreeFBS in Mechanical Engineering 9.529e-01 2.154e-01 4.425
## degreeFBS in Mining Engineering 1.889e-01 3.589e-01 0.526
## degreeFBS in Petroleum & Natl Gas Eng 7.418e-01 2.331e-01 3.183
## degreeFBS in Physical Education 1.120e+00 2.907e-01 3.852
## degreeFBS in Recreation -2.438e-01 4.507e-01 -0.541
## degreeFDegree Not Declared 3.425e-01 2.056e-01 1.665
## degreeFRegents Bachelor of Arts -4.241e-01 8.498e-01 -0.499
## studentLocAR -6.472e-01 9.796e-01 -0.661
## studentLocBC 2.087e+00 9.709e-01 2.149
## studentLocCA 4.130e-01 5.233e-01 0.789
## studentLocCO 9.177e-01 6.173e-01 1.487
## studentLocCT -5.150e-01 5.195e-01 -0.991
## studentLocDC -2.124e-01 5.422e-01 -0.392
## studentLocDE 1.802e-02 5.298e-01 0.034
## studentLocFL -1.443e-02 5.098e-01 -0.028
## studentLocFR 6.478e-01 5.268e-01 1.230
## studentLocGA 2.825e-01 5.207e-01 0.542
## studentLocIL 3.778e-01 5.301e-01 0.713
## studentLocIN 1.183e+00 5.738e-01 2.062
## studentLocKY -2.906e-01 5.859e-01 -0.496
## studentLocLA 1.489e+00 9.680e-01 1.538
## studentLocMA -2.676e-01 5.280e-01 -0.507
## studentLocMD -2.494e-01 4.935e-01 -0.505
## studentLocME -1.325e-01 7.677e-01 -0.173
## studentLocMI 8.461e-01 5.583e-01 1.515
## studentLocMN 1.075e+00 6.899e-01 1.557
## studentLocMO 4.968e-01 9.677e-01 0.513
## studentLocMS 4.316e-01 9.681e-01 0.446
## studentLocMT 1.873e+00 9.707e-01 1.929
## studentLocNC 3.136e-01 5.245e-01 0.598
## studentLocNH -6.674e-01 6.183e-01 -1.079
## studentLocNJ -1.194e-01 4.953e-01 -0.241
## studentLocNV 5.841e-01 6.890e-01 0.848
## studentLocNY -9.938e-02 4.975e-01 -0.200
## studentLocOH -2.020e-01 4.951e-01 -0.408
## studentLocOK 1.590e+00 9.683e-01 1.642
## studentLocON 1.599e+00 6.461e-01 2.475
## studentLocOR 3.386e-01 7.676e-01 0.441
## studentLocPA 7.746e-02 4.930e-01 0.157
## studentLocPR 1.310e+00 9.692e-01 1.352
## studentLocRI -3.191e-02 7.672e-01 -0.042
## studentLocSC 3.846e-01 5.525e-01 0.696
## studentLocSD -1.349e+00 9.704e-01 -1.390
## studentLocTN 1.903e-01 5.370e-01 0.354
## studentLocTX 8.358e-01 5.145e-01 1.624
## studentLocUT 4.600e-02 9.688e-01 0.047
## studentLocVA -2.396e-01 4.937e-01 -0.485
## studentLocVT -3.640e-01 6.475e-01 -0.562
## studentLocWA 2.328e-01 7.710e-01 0.302
## studentLocWI 3.148e-01 5.844e-01 0.539
## studentLocWV -4.570e-01 4.931e-01 -0.927
## proxStudentTypeLong Commute -3.421e-02 7.857e-02 -0.435
## proxStudentTypeShort Commute 2.836e-01 3.901e-02 7.268
## affinityStatusNo Affinity 1.031e-01 2.605e-02 3.960
## expectedFamContrib -4.893e-04 5.771e-04 -0.848
## expectedFamContrib.NATRUE 5.555e-02 7.888e-02 0.704
## aidStudentnonWVUReceived other aid -1.024e-01 4.377e-02 -2.340
## aidStudentPromScholarIs Promise -2.178e-01 4.090e-02 -5.326
## highestACT 1.418e-02 1.137e-03 12.473
## highestACT.NATRUE 8.026e-01 7.157e-02 11.214
## totalSAT 1.614e-02 1.222e-03 13.211
## totalSAT.NATRUE 7.961e-01 7.509e-02 10.602
## totalAwardnonWVU -1.962e-06 2.200e-06 -0.892
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## studentGenderM 0.206177
## studentEthnBlack 1.26e-13 ***
## studentEthnHispanic 0.039768 *
## studentEthnAsian 0.710125
## studentEthnNative 0.078508 .
## studentEthnUnknown 0.362170
## degreeFAssociate of Arts 0.239690
## degreeFBachelor Engr Tech 0.002368 **
## degreeFBachelor of Arts 0.000146 ***
## degreeFBachelor of Fine Arts 0.021136 *
## degreeFBachelor of Multidisc. Studies 0.025071 *
## degreeFBachelor of Music 6.43e-07 ***
## degreeFBachelor of Science 0.000179 ***
## degreeFBachelor of Science in Nursing 0.041516 *
## degreeFBachelor of Social Work 0.141097
## degreeFBS in Aerospace Engineering 6.33e-05 ***
## degreeFBS in Agriculture 0.064224 .
## degreeFBS in Biometric Systems 0.013465 *
## degreeFBS in Business Administration 0.000664 ***
## degreeFBS in Chemical Engineering 2.35e-05 ***
## degreeFBS in Civil Engineering 0.000334 ***
## degreeFBS in Computer Engineering 0.024309 *
## degreeFBS in Computer Science 3.79e-05 ***
## degreeFBS in Electrical Engineering 0.000154 ***
## degreeFBS in Forestry 0.233577
## degreeFBS in Industrial Engineering 8.53e-05 ***
## degreeFBS in Journalism 0.000239 ***
## degreeFBS in Landscape Architecture 0.012027 *
## degreeFBS in Mechanical Engineering 9.90e-06 ***
## degreeFBS in Mining Engineering 0.598587
## degreeFBS in Petroleum & Natl Gas Eng 0.001469 **
## degreeFBS in Physical Education 0.000119 ***
## degreeFBS in Recreation 0.588619
## degreeFDegree Not Declared 0.095910 .
## degreeFRegents Bachelor of Arts 0.617754
## studentLocAR 0.508875
## studentLocBC 0.031680 *
## studentLocCA 0.429966
## studentLocCO 0.137166
## studentLocCT 0.321599
## studentLocDC 0.695303
## studentLocDE 0.972871
## studentLocFL 0.977421
## studentLocFR 0.218910
## studentLocGA 0.587503
## studentLocIL 0.476037
## studentLocIN 0.039246 *
## studentLocKY 0.619919
## studentLocLA 0.124026
## studentLocMA 0.612365
## studentLocMD 0.613309
## studentLocME 0.863020
## studentLocMI 0.129722
## studentLocMN 0.119429
## studentLocMO 0.607717
## studentLocMS 0.655769
## studentLocMT 0.053750 .
## studentLocNC 0.549873
## studentLocNH 0.280443
## studentLocNJ 0.809446
## studentLocNV 0.396612
## studentLocNY 0.841699
## studentLocOH 0.683316
## studentLocOK 0.100668
## studentLocON 0.013344 *
## studentLocOR 0.659147
## studentLocPA 0.875155
## studentLocPR 0.176590
## studentLocRI 0.966826
## studentLocSC 0.486458
## studentLocSD 0.164525
## studentLocTN 0.723025
## studentLocTX 0.104373
## studentLocUT 0.962135
## studentLocVA 0.627505
## studentLocVT 0.574063
## studentLocWA 0.762663
## studentLocWI 0.590179
## studentLocWV 0.354102
## proxStudentTypeLong Commute 0.663263
## proxStudentTypeShort Commute 4.30e-13 ***
## affinityStatusNo Affinity 7.62e-05 ***
## expectedFamContrib 0.396488
## expectedFamContrib.NATRUE 0.481293
## aidStudentnonWVUReceived other aid 0.019344 *
## aidStudentPromScholarIs Promise 1.05e-07 ***
## highestACT < 2e-16 ***
## highestACT.NATRUE < 2e-16 ***
## totalSAT < 2e-16 ***
## totalSAT.NATRUE < 2e-16 ***
## totalAwardnonWVU 0.372655
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8323 on 4304 degrees of freedom
## Multiple R-squared: 0.265, Adjusted R-squared: 0.2495
## F-statistic: 17.06 on 91 and 4304 DF, p-value: < 2.2e-16anova(modWVUAid_3)## Analysis of Variance Table
##
## Response: log(totalAwardWVU)
## Df Sum Sq Mean Sq F value Pr(>F)
## studentGender 1 21.55 21.549 31.1057 2.593e-08 ***
## studentEthn 5 55.42 11.085 16.0008 1.177e-15 ***
## degreeF 29 234.38 8.082 11.6667 < 2.2e-16 ***
## studentLoc 44 384.10 8.730 12.6011 < 2.2e-16 ***
## proxStudentType 2 70.79 35.393 51.0893 < 2.2e-16 ***
## affinityStatus 1 7.77 7.769 11.2140 0.0008188 ***
## expectedFamContrib 1 0.88 0.882 1.2726 0.2593360
## expectedFamContrib.NA 1 3.79 3.788 5.4677 0.0194162 *
## aidStudentnonWVU 1 13.16 13.158 18.9929 1.343e-05 ***
## aidStudentPromScholar 1 0.83 0.827 1.1939 0.2746112
## highestACT 1 26.34 26.339 38.0204 7.644e-10 ***
## highestACT.NA 1 129.19 129.192 186.4876 < 2.2e-16 ***
## totalSAT 1 47.31 47.313 68.2967 < 2.2e-16 ***
## totalSAT.NA 1 79.12 79.123 114.2140 < 2.2e-16 ***
## totalAwardnonWVU 1 0.55 0.551 0.7950 0.3726546
## Residuals 4304 2981.66 0.693
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ncvTest(modWVUAid_3) ## Non-constant Variance Score Test
## Variance formula: ~ fitted.values
## Chisquare = 7.722425 Df = 1 p = 0.005453909plot(modWVUAid_3) ## Warning: not plotting observations with leverage one:
## 2168, 2288, 4123, 4238, 4358, 4374
## Warning: not plotting observations with leverage one:
## 2168, 2288, 4123, 4238, 4358, 4374
## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produced## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produced
mmp(modWVUAid_3, sd = TRUE)
residualPlot(modWVUAid_3)
summary(modWVUAid_3)##
## Call:
## lm(formula = log(totalAwardWVU) ~ studentGender + studentEthn +
## degreeF + studentLoc + proxStudentType + affinityStatus +
## expectedFamContrib + expectedFamContrib.NA + aidStudentnonWVU +
## aidStudentPromScholar + highestACT + highestACT.NA + totalSAT +
## totalSAT.NA + totalAwardnonWVU, data = finDataTableWVU_AL12)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.8253 -0.4349 0.0438 0.4598 2.9691
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 5.848e+00 5.285e-01 11.064
## studentGenderM 3.377e-02 2.671e-02 1.264
## studentEthnBlack 5.234e-01 7.040e-02 7.434
## studentEthnHispanic 3.127e-01 1.520e-01 2.057
## studentEthnAsian 4.465e-02 1.201e-01 0.372
## studentEthnNative 5.226e-01 2.970e-01 1.760
## studentEthnUnknown 2.545e-02 2.793e-02 0.911
## degreeFAssociate of Arts 2.050e-01 1.743e-01 1.176
## degreeFBachelor Engr Tech 1.553e+00 5.107e-01 3.042
## degreeFBachelor of Arts 6.537e-01 1.720e-01 3.802
## degreeFBachelor of Fine Arts 4.693e-01 2.035e-01 2.306
## degreeFBachelor of Multidisc. Studies 4.366e-01 1.948e-01 2.241
## degreeFBachelor of Music 1.000e+00 2.007e-01 4.985
## degreeFBachelor of Science 6.412e-01 1.710e-01 3.751
## degreeFBachelor of Science in Nursing 7.286e-01 3.573e-01 2.039
## degreeFBachelor of Social Work 3.920e-01 2.663e-01 1.472
## degreeFBS in Aerospace Engineering 9.210e-01 2.300e-01 4.004
## degreeFBS in Agriculture 4.291e-01 2.318e-01 1.851
## degreeFBS in Biometric Systems 1.014e+00 4.100e-01 2.472
## degreeFBS in Business Administration 5.981e-01 1.756e-01 3.406
## degreeFBS in Chemical Engineering 9.829e-01 2.322e-01 4.233
## degreeFBS in Civil Engineering 7.868e-01 2.192e-01 3.590
## degreeFBS in Computer Engineering 5.770e-01 2.561e-01 2.253
## degreeFBS in Computer Science 8.690e-01 2.107e-01 4.124
## degreeFBS in Electrical Engineering 8.836e-01 2.333e-01 3.787
## degreeFBS in Forestry 3.366e-01 2.825e-01 1.191
## degreeFBS in Industrial Engineering 1.038e+00 2.639e-01 3.933
## degreeFBS in Journalism 6.834e-01 1.859e-01 3.677
## degreeFBS in Landscape Architecture 6.679e-01 2.658e-01 2.512
## degreeFBS in Mechanical Engineering 9.529e-01 2.154e-01 4.425
## degreeFBS in Mining Engineering 1.889e-01 3.589e-01 0.526
## degreeFBS in Petroleum & Natl Gas Eng 7.418e-01 2.331e-01 3.183
## degreeFBS in Physical Education 1.120e+00 2.907e-01 3.852
## degreeFBS in Recreation -2.438e-01 4.507e-01 -0.541
## degreeFDegree Not Declared 3.425e-01 2.056e-01 1.665
## degreeFRegents Bachelor of Arts -4.241e-01 8.498e-01 -0.499
## studentLocAR -6.472e-01 9.796e-01 -0.661
## studentLocBC 2.087e+00 9.709e-01 2.149
## studentLocCA 4.130e-01 5.233e-01 0.789
## studentLocCO 9.177e-01 6.173e-01 1.487
## studentLocCT -5.150e-01 5.195e-01 -0.991
## studentLocDC -2.124e-01 5.422e-01 -0.392
## studentLocDE 1.802e-02 5.298e-01 0.034
## studentLocFL -1.443e-02 5.098e-01 -0.028
## studentLocFR 6.478e-01 5.268e-01 1.230
## studentLocGA 2.825e-01 5.207e-01 0.542
## studentLocIL 3.778e-01 5.301e-01 0.713
## studentLocIN 1.183e+00 5.738e-01 2.062
## studentLocKY -2.906e-01 5.859e-01 -0.496
## studentLocLA 1.489e+00 9.680e-01 1.538
## studentLocMA -2.676e-01 5.280e-01 -0.507
## studentLocMD -2.494e-01 4.935e-01 -0.505
## studentLocME -1.325e-01 7.677e-01 -0.173
## studentLocMI 8.461e-01 5.583e-01 1.515
## studentLocMN 1.075e+00 6.899e-01 1.557
## studentLocMO 4.968e-01 9.677e-01 0.513
## studentLocMS 4.316e-01 9.681e-01 0.446
## studentLocMT 1.873e+00 9.707e-01 1.929
## studentLocNC 3.136e-01 5.245e-01 0.598
## studentLocNH -6.674e-01 6.183e-01 -1.079
## studentLocNJ -1.194e-01 4.953e-01 -0.241
## studentLocNV 5.841e-01 6.890e-01 0.848
## studentLocNY -9.938e-02 4.975e-01 -0.200
## studentLocOH -2.020e-01 4.951e-01 -0.408
## studentLocOK 1.590e+00 9.683e-01 1.642
## studentLocON 1.599e+00 6.461e-01 2.475
## studentLocOR 3.386e-01 7.676e-01 0.441
## studentLocPA 7.746e-02 4.930e-01 0.157
## studentLocPR 1.310e+00 9.692e-01 1.352
## studentLocRI -3.191e-02 7.672e-01 -0.042
## studentLocSC 3.846e-01 5.525e-01 0.696
## studentLocSD -1.349e+00 9.704e-01 -1.390
## studentLocTN 1.903e-01 5.370e-01 0.354
## studentLocTX 8.358e-01 5.145e-01 1.624
## studentLocUT 4.600e-02 9.688e-01 0.047
## studentLocVA -2.396e-01 4.937e-01 -0.485
## studentLocVT -3.640e-01 6.475e-01 -0.562
## studentLocWA 2.328e-01 7.710e-01 0.302
## studentLocWI 3.148e-01 5.844e-01 0.539
## studentLocWV -4.570e-01 4.931e-01 -0.927
## proxStudentTypeLong Commute -3.421e-02 7.857e-02 -0.435
## proxStudentTypeShort Commute 2.836e-01 3.901e-02 7.268
## affinityStatusNo Affinity 1.031e-01 2.605e-02 3.960
## expectedFamContrib -4.893e-04 5.771e-04 -0.848
## expectedFamContrib.NATRUE 5.555e-02 7.888e-02 0.704
## aidStudentnonWVUReceived other aid -1.024e-01 4.377e-02 -2.340
## aidStudentPromScholarIs Promise -2.178e-01 4.090e-02 -5.326
## highestACT 1.418e-02 1.137e-03 12.473
## highestACT.NATRUE 8.026e-01 7.157e-02 11.214
## totalSAT 1.614e-02 1.222e-03 13.211
## totalSAT.NATRUE 7.961e-01 7.509e-02 10.602
## totalAwardnonWVU -1.962e-06 2.200e-06 -0.892
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## studentGenderM 0.206177
## studentEthnBlack 1.26e-13 ***
## studentEthnHispanic 0.039768 *
## studentEthnAsian 0.710125
## studentEthnNative 0.078508 .
## studentEthnUnknown 0.362170
## degreeFAssociate of Arts 0.239690
## degreeFBachelor Engr Tech 0.002368 **
## degreeFBachelor of Arts 0.000146 ***
## degreeFBachelor of Fine Arts 0.021136 *
## degreeFBachelor of Multidisc. Studies 0.025071 *
## degreeFBachelor of Music 6.43e-07 ***
## degreeFBachelor of Science 0.000179 ***
## degreeFBachelor of Science in Nursing 0.041516 *
## degreeFBachelor of Social Work 0.141097
## degreeFBS in Aerospace Engineering 6.33e-05 ***
## degreeFBS in Agriculture 0.064224 .
## degreeFBS in Biometric Systems 0.013465 *
## degreeFBS in Business Administration 0.000664 ***
## degreeFBS in Chemical Engineering 2.35e-05 ***
## degreeFBS in Civil Engineering 0.000334 ***
## degreeFBS in Computer Engineering 0.024309 *
## degreeFBS in Computer Science 3.79e-05 ***
## degreeFBS in Electrical Engineering 0.000154 ***
## degreeFBS in Forestry 0.233577
## degreeFBS in Industrial Engineering 8.53e-05 ***
## degreeFBS in Journalism 0.000239 ***
## degreeFBS in Landscape Architecture 0.012027 *
## degreeFBS in Mechanical Engineering 9.90e-06 ***
## degreeFBS in Mining Engineering 0.598587
## degreeFBS in Petroleum & Natl Gas Eng 0.001469 **
## degreeFBS in Physical Education 0.000119 ***
## degreeFBS in Recreation 0.588619
## degreeFDegree Not Declared 0.095910 .
## degreeFRegents Bachelor of Arts 0.617754
## studentLocAR 0.508875
## studentLocBC 0.031680 *
## studentLocCA 0.429966
## studentLocCO 0.137166
## studentLocCT 0.321599
## studentLocDC 0.695303
## studentLocDE 0.972871
## studentLocFL 0.977421
## studentLocFR 0.218910
## studentLocGA 0.587503
## studentLocIL 0.476037
## studentLocIN 0.039246 *
## studentLocKY 0.619919
## studentLocLA 0.124026
## studentLocMA 0.612365
## studentLocMD 0.613309
## studentLocME 0.863020
## studentLocMI 0.129722
## studentLocMN 0.119429
## studentLocMO 0.607717
## studentLocMS 0.655769
## studentLocMT 0.053750 .
## studentLocNC 0.549873
## studentLocNH 0.280443
## studentLocNJ 0.809446
## studentLocNV 0.396612
## studentLocNY 0.841699
## studentLocOH 0.683316
## studentLocOK 0.100668
## studentLocON 0.013344 *
## studentLocOR 0.659147
## studentLocPA 0.875155
## studentLocPR 0.176590
## studentLocRI 0.966826
## studentLocSC 0.486458
## studentLocSD 0.164525
## studentLocTN 0.723025
## studentLocTX 0.104373
## studentLocUT 0.962135
## studentLocVA 0.627505
## studentLocVT 0.574063
## studentLocWA 0.762663
## studentLocWI 0.590179
## studentLocWV 0.354102
## proxStudentTypeLong Commute 0.663263
## proxStudentTypeShort Commute 4.30e-13 ***
## affinityStatusNo Affinity 7.62e-05 ***
## expectedFamContrib 0.396488
## expectedFamContrib.NATRUE 0.481293
## aidStudentnonWVUReceived other aid 0.019344 *
## aidStudentPromScholarIs Promise 1.05e-07 ***
## highestACT < 2e-16 ***
## highestACT.NATRUE < 2e-16 ***
## totalSAT < 2e-16 ***
## totalSAT.NATRUE < 2e-16 ***
## totalAwardnonWVU 0.372655
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8323 on 4304 degrees of freedom
## Multiple R-squared: 0.265, Adjusted R-squared: 0.2495
## F-statistic: 17.06 on 91 and 4304 DF, p-value: < 2.2e-16#test model predictions
names(finDataTableWVU_AL12)## [1] "rule49Grant" "instEmployAid"
## [3] "instGrantAcademic" "instGrantAthletic"
## [5] "instGrantOther" "studentGender"
## [7] "studentEthn" "degreeF"
## [9] "degreeType" "studentLoc"
## [11] "stateIndicator" "proxStudentType"
## [13] "highSchoolGPA" "prevColGPA"
## [15] "highestACT" "totalSAT"
## [17] "scoreGED" "scaledAcademAchiev"
## [19] "affinityStatus" "expectedFamContrib"
## [21] "totalAwardWVU" "totalAwardnonWVU"
## [23] "totalAwardPromScholar" "aidStudentWVU"
## [25] "aidStudentnonWVU" "aidStudentPromScholar"
## [27] "highSchoolGPA.NA" "prevColGPA.NA"
## [29] "highestACT.NA" "totalSAT.NA"
## [31] "scoreGED.NA" "expectedFamContrib.NA"
## [33] "studentEthn.NA" "scaledAcademAchiev.NA"which(finDataTableWVU_AL12[,21] > 40000)## [1] 813 2031 4053 4098 4124fitResults <- predict(modWVUAid_3, newdata = finDataTableWVU_AL12[813,], type = "response")
exp(fitResults)## 1355
## 2114.119finDataTableWVU_AL12[813, 21]## [1] 41170finDataTableWVU_AL12$predictedAwardWVU <-exp(predict(modWVUAid_3))```